{"url":"/sota/self-supervised-image-classification-on","task":{"name":"Self-Supervised Image Classification","url":"/task/self-supervised-image-classification","note":null},"dataset":{"name":"ImageNet","url":"/dataset/imagenet"},"category":null,"categories":["Adversarial","Audio","Computer Code","Computer Vision","Medical","Methodology","Miscellaneous","Music","Natural Language Processing","Reasoning","Speech"],"category_note":"the archive's category list for this table covers most areas; treated as no area assigned","description":"This is the task of image classification using representations learnt with self-supervised learning. Self-supervised methods generally involve a pretext task that is solved to learn a good representation and a loss function to learn with. One example of a loss function is an autoencoder based loss where the goal is reconstruction of an image pixel-by-pixel. A more popular recent example is a contrastive loss, which measure the similarity of sample pairs in a representation space, and where there can be a varying target instead of a fixed target to reconstruct (as in the case of autoencoders).\r\n\r\nA common evaluation protocol is to train a linear classifier on top of (frozen) representations learnt by self-supervised methods. The leaderboards for the linear evaluation protocol can be found below. In practice, it is more common to fine-tune features on a downstream task. An alternative evaluation protocol therefore uses semi-supervised learning and finetunes on a % of the labels. The leaderboards for the finetuning protocol can be accessed [here](https://paperswithcode.com/task/semi-supervised-image-classification).\r\n\r\nYou may want to read some blog posts before reading the papers and checking the leaderboards:\r\n\r\n- [Contrastive Self-Supervised Learning](https://ankeshanand.com/blog/2020/01/26/contrative-self-supervised-learning.html) - Ankesh Anand\r\n- [The Illustrated Self-Supervised Learning](https://amitness.com/2020/02/illustrated-self-supervised-learning/) - Amit Chaudhary\r\n- [Self-supervised learning and computer vision](https://www.fast.ai/2020/01/13/self_supervised/) - Jeremy Howard\r\n- [Self-Supervised Representation Learning](https://lilianweng.github.io/lil-log/2019/11/10/self-supervised-learning.html) - Lilian Weng\r\n\r\nThere is also Yann LeCun's talk at AAAI-20 which you can watch [here](https://vimeo.com/390347111) (35:00+).\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [A Simple Framework for Contrastive Learning of Visual Representations](https://arxiv.org/pdf/2002.05709v1.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Top 1 Accuracy","Top 5 Accuracy","Number of Params"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Top 1 Accuracy":"higher","Top 5 Accuracy":"higher","Number of Params":"lower"}},"counts":{"rows":144,"rows_with_code":135,"rows_with_paper_page":144,"rows_dated":144,"rows_using_additional_data":12},"rows":[{"rank_in_archive_order":1,"model":"DINOv2+reg (ViT-g/14)","metrics":{"Number of Params":"1100M","Top 1 Accuracy":"87.1"},"uses_additional_data":true,"paper_date":"2023-09-28","paper":"/paper/vision-transformers-need-registers","paper_url":"https://arxiv.org/abs/2309.16588v2","paper_title":"Vision Transformers Need Registers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":4,"n_unverified":16,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":2,"model":"DINOv2 (ViT-g/14 @448)","metrics":{"Number of Params":"1100M","Top 1 Accuracy":"86.7%"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":3,"model":"DINOv2 (ViT-g/14)","metrics":{"Number of Params":"1100M","Top 1 Accuracy":"86.5%"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":4,"model":"DINOv2 distilled (ViT-L/14)","metrics":{"Number of Params":"307M","Top 1 Accuracy":"86.3%"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":5,"model":"MIM-Refiner (D2V2-ViT-H/14)","metrics":{"Number of Params":"632M","Top 1 Accuracy":"84.7%"},"uses_additional_data":false,"paper_date":"2024-02-15","paper":"/paper/mim-refiner-a-contrastive-learning-boost-from","paper_url":"https://arxiv.org/abs/2402.10093v3","paper_title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","code":"https://github.com/ml-jku/MIM-Refiner","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"MIM-Refiner (MAE-ViT-2B/14)","metrics":{"Number of Params":"1890M","Top 1 Accuracy":"84.5%"},"uses_additional_data":false,"paper_date":"2024-02-15","paper":"/paper/mim-refiner-a-contrastive-learning-boost-from","paper_url":"https://arxiv.org/abs/2402.10093v3","paper_title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","code":"https://github.com/ml-jku/MIM-Refiner","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"DINOv2 distilled (ViT-B/14)","metrics":{"Number of Params":"85M","Top 1 Accuracy":"84.5%"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":8,"model":"MIM-Refiner (MAE-ViT-H/14","metrics":{"Number of Params":"632M","Top 1 Accuracy":"83.7%"},"uses_additional_data":false,"paper_date":"2024-02-15","paper":"/paper/mim-refiner-a-contrastive-learning-boost-from","paper_url":"https://arxiv.org/abs/2402.10093v3","paper_title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","code":"https://github.com/ml-jku/MIM-Refiner","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"MIM-Refiner (D2V2-ViT-L/16)","metrics":{"Number of Params":"307M","Top 1 Accuracy":"83.5%"},"uses_additional_data":false,"paper_date":"2024-02-15","paper":"/paper/mim-refiner-a-contrastive-learning-boost-from","paper_url":"https://arxiv.org/abs/2402.10093v3","paper_title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","code":"https://github.com/ml-jku/MIM-Refiner","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"MIM-Refiner (MAE-ViT-L/16)","metrics":{"Number of Params":"307M","Top 1 Accuracy":"82.8%"},"uses_additional_data":false,"paper_date":"2024-02-15","paper":"/paper/mim-refiner-a-contrastive-learning-boost-from","paper_url":"https://arxiv.org/abs/2402.10093v3","paper_title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","code":"https://github.com/ml-jku/MIM-Refiner","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"iBOT (ViT-L/16) (IN22k)","metrics":{"Number of Params":"307M","Top 1 Accuracy":"82.3%"},"uses_additional_data":true,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"MAE-CT (ViT-H/16)","metrics":{"Number of Params":"632M","Top 1 Accuracy":"82.2%"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/contrastive-tuning-a-little-help-to-make","paper_url":"https://arxiv.org/abs/2304.10520v2","paper_title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","code":"https://github.com/ml-jku/mae-ct","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Mugs (VIT-L/16)","metrics":{"Number of Params":"307M","Top 1 Accuracy":"82.1%"},"uses_additional_data":false,"paper_date":"2022-03-27","paper":"/paper/mugs-a-multi-granular-self-supervised","paper_url":"https://arxiv.org/abs/2203.14415v1","paper_title":"Mugs: A Multi-Granular Self-Supervised Learning Framework","code":"https://github.com/sail-sg/mugs","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":17,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"MAE-CT (ViT-L/16","metrics":{"Number of Params":"307M","Top 1 Accuracy":"81.5%"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/contrastive-tuning-a-little-help-to-make","paper_url":"https://arxiv.org/abs/2304.10520v2","paper_title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","code":"https://github.com/ml-jku/mae-ct","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"EsViT (Swin-B)","metrics":{"Number of Params":"87M","Top 1 Accuracy":"81.3","Top 5 Accuracy":"95.5"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/efficient-self-supervised-vision-transformers","paper_url":"https://arxiv.org/abs/2106.09785v2","paper_title":"Efficient Self-supervised Vision Transformers for Representation Learning","code":"https://github.com/microsoft/esvit","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"iBOT (ViT-L/16)","metrics":{"Number of Params":"307M","Top 1 Accuracy":"81.3%"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"DINOv2 distilled (ViT-S/14)","metrics":{"Number of Params":"21M","Top 1 Accuracy":"81.1%"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":18,"model":"MoCo v3 (ViT-BN-L/7)","metrics":{"Number of Params":"304M","Top 1 Accuracy":"81.0%"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/an-empirical-study-of-training-self","paper_url":"https://arxiv.org/abs/2104.02057v4","paper_title":"An Empirical Study of Training Self-Supervised Vision Transformers","code":"https://github.com/open-mmlab/mmselfsup","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":19,"model":"EsViT(Swin-S)","metrics":{"Number of Params":"49M","Top 1 Accuracy":"80.8"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/efficient-self-supervised-vision-transformers","paper_url":"https://arxiv.org/abs/2106.09785v2","paper_title":"Efficient Self-supervised Vision Transformers for Representation Learning","code":"https://github.com/microsoft/esvit","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"MSN (ViT-L/7)","metrics":{"Number of Params":"306M","Top 1 Accuracy":"80.7%"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/masked-siamese-networks-for-label-efficient","paper_url":"https://arxiv.org/abs/2204.07141v1","paper_title":"Masked Siamese Networks for Label-Efficient Learning","code":"https://github.com/lightly-ai/lightly","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"ReLICv2 (ResNet-200 x2)","metrics":{"Number of Params":"250M","Top 1 Accuracy":"80.6%"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"MR BarTwins (MR BarTwins)","metrics":{"Top 1 Accuracy":"80.4%"},"uses_additional_data":false,"paper_date":"2022-11-15","paper":"/paper/masked-reconstruction-contrastive-learning","paper_url":"https://arxiv.org/abs/2211.09013v1","paper_title":"Masked Reconstruction Contrastive Learning with Information Bottleneck Principle","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"DiGIT","metrics":{"Number of Params":"732M","Top 1 Accuracy":"80.3%"},"uses_additional_data":false,"paper_date":"2024-10-16","paper":"/paper/stabilize-the-latent-space-for-image","paper_url":"https://arxiv.org/abs/2410.12490v2","paper_title":"Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective","code":"https://github.com/DAMO-NLP-SG/DiGIT","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"iBOT-vMF (ViT-B/16)","metrics":{"Number of Params":"85M","Top 1 Accuracy":"80.3%"},"uses_additional_data":false,"paper_date":"2024-05-17","paper":"/paper/dino-as-a-von-mises-fisher-mixture-model-1","paper_url":"https://arxiv.org/abs/2405.10939v1","paper_title":"DINO as a von Mises-Fisher mixture model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"DINO (xcit_medium_24_p8)","metrics":{"Number of Params":"84M","Top 1 Accuracy":"80.3%"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/emerging-properties-in-self-supervised-vision","paper_url":"https://arxiv.org/abs/2104.14294v2","paper_title":"Emerging Properties in Self-Supervised Vision Transformers","code":"https://github.com/facebookresearch/dino","n_code_links":32,"syntology":{"n_ran":5,"n_unverified":15,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":26,"model":"PGT (PGT-B w/ Flow)","metrics":{"Number of Params":"70M","Top 1 Accuracy":"80.3%"},"uses_additional_data":false,"paper_date":"2023-11-30","paper":"/paper/perceptual-group-tokenizer-building","paper_url":"https://arxiv.org/abs/2311.18296v2","paper_title":"Perceptual Group Tokenizer: Building Perception with Iterative Grouping","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"DINO (ViT-B/8)","metrics":{"Number of Params":"80M","Top 1 Accuracy":"80.1%"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/emerging-properties-in-self-supervised-vision","paper_url":"https://arxiv.org/abs/2104.14294v2","paper_title":"Emerging Properties in Self-Supervised Vision Transformers","code":"https://github.com/facebookresearch/dino","n_code_links":32,"syntology":{"n_ran":5,"n_unverified":15,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":28,"model":"SimCLRv2 (ResNet-152 x3, SK)","metrics":{"Number of Params":"795M","Top 1 Accuracy":"79.8%","Top 5 Accuracy":"94.9%"},"uses_additional_data":false,"paper_date":"2020-06-17","paper":"/paper/big-self-supervised-models-are-strong-semi","paper_url":"https://arxiv.org/abs/2006.10029v2","paper_title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","code":"https://github.com/google-research/simclr","n_code_links":9,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"SEERv2","metrics":{"Number of Params":"10000M","Top 1 Accuracy":"79.8%"},"uses_additional_data":true,"paper_date":"2022-02-16","paper":"/paper/vision-models-are-more-robust-and-fair-when","paper_url":"https://arxiv.org/abs/2202.08360v2","paper_title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","code":"https://github.com/facebookresearch/vissl","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"PercMAE (ViT-B, dVAE)","metrics":{"Number of Params":"80M","Top 1 Accuracy":"79.8%"},"uses_additional_data":true,"paper_date":"2022-12-30","paper":"/paper/improving-visual-representation-learning","paper_url":"https://arxiv.org/abs/2212.14504v2","paper_title":"Improving Visual Representation Learning through Perceptual Understanding","code":"https://github.com/tractableai/perceptual-mae","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"ReLICv2 (ResNet200)","metrics":{"Number of Params":"63M","Top 1 Accuracy":"79.8%"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"DINO (ViT-S/8)","metrics":{"Number of Params":"21M","Top 1 Accuracy":"79.7%"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/emerging-properties-in-self-supervised-vision","paper_url":"https://arxiv.org/abs/2104.14294v2","paper_title":"Emerging Properties in Self-Supervised Vision Transformers","code":"https://github.com/facebookresearch/dino","n_code_links":32,"syntology":{"n_ran":5,"n_unverified":15,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":33,"model":"BYOL (ResNet-200 x2)","metrics":{"Number of Params":"250M","Top 1 Accuracy":"79.6%","Top 5 Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2020-06-13","paper":"/paper/bootstrap-your-own-latent-a-new-approach-to","paper_url":"https://arxiv.org/abs/2006.07733v3","paper_title":"Bootstrap your own latent: A new approach to self-supervised Learning","code":"https://github.com/deepmind/deepmind-research/tree/master/byol","n_code_links":31,"syntology":{"n_ran":62,"n_unverified":17,"n_samples":79,"n_pointer_only_licence":46}},{"rank_in_archive_order":34,"model":"ReLICv2 (ResNet-50 4x)","metrics":{"Number of Params":"375M","Top 1 Accuracy":"79.4%"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"ReLICv2 (ResNet152)","metrics":{"Number of Params":"58M","Top 1 Accuracy":"79.3%"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"BAM (CAFormer-M36)","metrics":{"Top 1 Accuracy":"79.3%"},"uses_additional_data":false,"paper_date":"2024-08-04","paper":"/paper/2408-02014","paper_url":"https://arxiv.org/abs/2408.02014v1","paper_title":"Unsupervised Representation Learning by Balanced Self Attention Matching","code":"https://github.com/danielshalam/bam","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"MoCo v3 (ViT-BN-H)","metrics":{"Number of Params":"700M","Top 1 Accuracy":"79.1%"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/an-empirical-study-of-training-self","paper_url":"https://arxiv.org/abs/2104.02057v4","paper_title":"An Empirical Study of Training Self-Supervised Vision Transformers","code":"https://github.com/open-mmlab/mmselfsup","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":38,"model":"Unicom (ViT-B/16)","metrics":{"Number of Params":"80M","Top 1 Accuracy":"79.1%"},"uses_additional_data":true,"paper_date":"2023-04-12","paper":"/paper/unicom-universal-and-compact-representation","paper_url":"https://arxiv.org/abs/2304.05884v1","paper_title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","code":"https://github.com/OML-Team/open-metric-learning","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":39,"model":"SMoG (ResNet-50 x4)","metrics":{"Number of Params":"375M","Top 1 Accuracy":"79.0%","Top 5 Accuracy":"94.4"},"uses_additional_data":false,"paper_date":"2022-07-13","paper":"/paper/unsupervised-visual-representation-learning-4","paper_url":"https://arxiv.org/abs/2207.06167v1","paper_title":"Unsupervised Visual Representation Learning by Synchronous Momentum Grouping","code":"https://github.com/lightly-ai/lightly","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"ReLICv2 (ResNet-50 x2)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"79%"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"C-BYOL (ResNet-50 2x, 1000 epochs)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"78.8%","Top 5 Accuracy":"94.5%"},"uses_additional_data":false,"paper_date":"2021-09-27","paper":"/paper/compressive-visual-representations","paper_url":"https://arxiv.org/abs/2109.12909v3","paper_title":"Compressive Visual Representations","code":"https://github.com/google-research/compressive-visual-representations","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"DINO-vMF (ViT-B/16)","metrics":{"Number of Params":"85M","Top 1 Accuracy":"78.8%"},"uses_additional_data":false,"paper_date":"2024-05-17","paper":"/paper/dino-as-a-von-mises-fisher-mixture-model-1","paper_url":"https://arxiv.org/abs/2405.10939v1","paper_title":"DINO as a von Mises-Fisher mixture model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":43,"model":"ReLICv2 (ResNet101)","metrics":{"Number of Params":"44M","Top 1 Accuracy":"78.7%"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"BYOL (ResNet-50 x4)","metrics":{"Number of Params":"375M","Top 1 Accuracy":"78.6%","Top 5 Accuracy":"94.2%"},"uses_additional_data":false,"paper_date":"2020-06-13","paper":"/paper/bootstrap-your-own-latent-a-new-approach-to","paper_url":"https://arxiv.org/abs/2006.07733v3","paper_title":"Bootstrap your own latent: A new approach to self-supervised Learning","code":"https://github.com/deepmind/deepmind-research/tree/master/byol","n_code_links":31,"syntology":{"n_ran":62,"n_unverified":17,"n_samples":79,"n_pointer_only_licence":46}},{"rank_in_archive_order":45,"model":"SwAV (ResNet-50 x5)","metrics":{"Number of Params":"586M","Top 1 Accuracy":"78.5%"},"uses_additional_data":false,"paper_date":"2020-06-17","paper":"/paper/unsupervised-learning-of-visual-features-by","paper_url":"https://arxiv.org/abs/2006.09882v5","paper_title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","code":"https://github.com/open-mmlab/mmdetection","n_code_links":18,"syntology":{"n_ran":13,"n_unverified":4,"n_samples":17,"n_pointer_only_licence":6}},{"rank_in_archive_order":46,"model":"DINO (ViT-B/16)","metrics":{"Number of Params":"85M","Top 1 Accuracy":"78.2%"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/emerging-properties-in-self-supervised-vision","paper_url":"https://arxiv.org/abs/2104.14294v2","paper_title":"Emerging Properties in Self-Supervised Vision Transformers","code":"https://github.com/facebookresearch/dino","n_code_links":32,"syntology":{"n_ran":5,"n_unverified":15,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":47,"model":"MoCo v3 (ViT-H)","metrics":{"Number of Params":"632M","Top 1 Accuracy":"78.1%"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/an-empirical-study-of-training-self","paper_url":"https://arxiv.org/abs/2104.02057v4","paper_title":"An Empirical Study of Training Self-Supervised Vision Transformers","code":"https://github.com/open-mmlab/mmselfsup","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":48,"model":"PercMAE (ViT-B)","metrics":{"Number of Params":"80M","Top 1 Accuracy":"78.1%"},"uses_additional_data":false,"paper_date":"2022-12-30","paper":"/paper/improving-visual-representation-learning","paper_url":"https://arxiv.org/abs/2212.14504v2","paper_title":"Improving Visual Representation Learning through Perceptual Understanding","code":"https://github.com/tractableai/perceptual-mae","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"BAM (ViT-B/16)","metrics":{"Number of Params":"80M","Top 1 Accuracy":"78.1%"},"uses_additional_data":false,"paper_date":"2024-08-04","paper":"/paper/2408-02014","paper_url":"https://arxiv.org/abs/2408.02014v1","paper_title":"Unsupervised Representation Learning by Balanced Self Attention Matching","code":"https://github.com/danielshalam/bam","n_code_links":1,"syntology":null},{"rank_in_archive_order":50,"model":"SMoG (ResNet-50 x2)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"78.0%","Top 5 Accuracy":"93.9"},"uses_additional_data":false,"paper_date":"2022-07-13","paper":"/paper/unsupervised-visual-representation-learning-4","paper_url":"https://arxiv.org/abs/2207.06167v1","paper_title":"Unsupervised Visual Representation Learning by Synchronous Momentum Grouping","code":"https://github.com/lightly-ai/lightly","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":51,"model":"MoCo v3 (ViT-L)","metrics":{"Number of Params":"307M","Top 1 Accuracy":"77.6%"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/an-empirical-study-of-training-self","paper_url":"https://arxiv.org/abs/2104.02057v4","paper_title":"An Empirical Study of Training Self-Supervised Vision Transformers","code":"https://github.com/open-mmlab/mmselfsup","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":52,"model":"SEER","metrics":{"Number of Params":"1300M","Top 1 Accuracy":"77.5%"},"uses_additional_data":true,"paper_date":"2021-03-02","paper":"/paper/self-supervised-pretraining-of-visual","paper_url":"https://arxiv.org/abs/2103.01988v2","paper_title":"Self-supervised Pretraining of Visual Features in the Wild","code":"https://github.com/facebookresearch/vissl","n_code_links":1,"syntology":null},{"rank_in_archive_order":53,"model":"BYOL (ResNet-50 x2)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"77.4%","Top 5 Accuracy":"93.6%"},"uses_additional_data":false,"paper_date":"2020-06-13","paper":"/paper/bootstrap-your-own-latent-a-new-approach-to","paper_url":"https://arxiv.org/abs/2006.07733v3","paper_title":"Bootstrap your own latent: A new approach to self-supervised Learning","code":"https://github.com/deepmind/deepmind-research/tree/master/byol","n_code_links":31,"syntology":{"n_ran":62,"n_unverified":17,"n_samples":79,"n_pointer_only_licence":46}},{"rank_in_archive_order":54,"model":"SwAV (ResNet-50 x2)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"77.3%"},"uses_additional_data":false,"paper_date":"2020-06-17","paper":"/paper/unsupervised-learning-of-visual-features-by","paper_url":"https://arxiv.org/abs/2006.09882v5","paper_title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","code":"https://github.com/open-mmlab/mmdetection","n_code_links":18,"syntology":{"n_ran":13,"n_unverified":4,"n_samples":17,"n_pointer_only_licence":6}},{"rank_in_archive_order":55,"model":"ReLICv2 (ResNet-50)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"77.1%"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":56,"model":"DINO (ViT-S/16)","metrics":{"Number of Params":"21M","Top 1 Accuracy":"77.0%"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/emerging-properties-in-self-supervised-vision","paper_url":"https://arxiv.org/abs/2104.14294v2","paper_title":"Emerging Properties in Self-Supervised Vision Transformers","code":"https://github.com/facebookresearch/dino","n_code_links":32,"syntology":{"n_ran":5,"n_unverified":15,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":57,"model":"DINO-vMF (ViT-S/16)","metrics":{"Number of Params":"21M","Top 1 Accuracy":"77.0%"},"uses_additional_data":false,"paper_date":"2024-05-17","paper":"/paper/dino-as-a-von-mises-fisher-mixture-model-1","paper_url":"https://arxiv.org/abs/2405.10939v1","paper_title":"DINO as a von Mises-Fisher mixture model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":58,"model":"MoCo v3 (ViT-B/16)","metrics":{"Number of Params":"86M","Top 1 Accuracy":"76.7%"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/an-empirical-study-of-training-self","paper_url":"https://arxiv.org/abs/2104.02057v4","paper_title":"An Empirical Study of Training Self-Supervised Vision Transformers","code":"https://github.com/open-mmlab/mmselfsup","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":59,"model":"MAE (ViT-H)","metrics":{"Number of Params":"700M","Top 1 Accuracy":"76.6%"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/masked-autoencoders-are-scalable-vision","paper_url":"https://arxiv.org/abs/2111.06377v2","paper_title":"Masked Autoencoders Are Scalable Vision Learners","code":"https://github.com/facebookresearch/mae","n_code_links":58,"syntology":{"n_ran":71,"n_unverified":66,"n_samples":137,"n_pointer_only_licence":73}},{"rank_in_archive_order":60,"model":"SimCLR (ResNet-50 4x)","metrics":{"Number of Params":"375M","Top 1 Accuracy":"76.5%","Top 5 Accuracy":"93.2%"},"uses_additional_data":false,"paper_date":"2020-02-13","paper":"/paper/a-simple-framework-for-contrastive-learning","paper_url":"https://arxiv.org/abs/2002.05709v3","paper_title":"A Simple Framework for Contrastive Learning of Visual Representations","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/simclr","n_code_links":96,"syntology":{"n_ran":79,"n_unverified":58,"n_samples":137,"n_pointer_only_licence":52}},{"rank_in_archive_order":61,"model":"CoKe (ResNet-50)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"76.4%"},"uses_additional_data":false,"paper_date":"2021-05-24","paper":"/paper/unsupervised-visual-representation-learning-3","paper_url":"https://arxiv.org/abs/2105.11527v3","paper_title":"Unsupervised Visual Representation Learning by Online Constrained K-Means","code":"https://github.com/idstcv/coke","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":62,"model":"SMoG (ResNet-50)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"76.4%"},"uses_additional_data":false,"paper_date":"2022-07-13","paper":"/paper/unsupervised-visual-representation-learning-4","paper_url":"https://arxiv.org/abs/2207.06167v1","paper_title":"Unsupervised Visual Representation Learning by Synchronous Momentum Grouping","code":"https://github.com/lightly-ai/lightly","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":63,"model":"ReSSL (ResNet-50 w/ Predictor and Stronger Aug)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"76.3%"},"uses_additional_data":false,"paper_date":"2022-03-16","paper":"/paper/relational-self-supervised-learning","paper_url":"https://arxiv.org/abs/2203.08717v3","paper_title":"Weak Augmentation Guided Relational Self-Supervised Learning","code":"https://github.com/mingkai-zheng/ReSSL","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":64,"model":"ReSSL (ResNet-50 w/ Predictor)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"76.0%"},"uses_additional_data":false,"paper_date":"2022-03-16","paper":"/paper/relational-self-supervised-learning","paper_url":"https://arxiv.org/abs/2203.08717v3","paper_title":"Weak Augmentation Guided Relational Self-Supervised Learning","code":"https://github.com/mingkai-zheng/ReSSL","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":65,"model":"Triplet  (ResNet-50)","metrics":{"Number of Params":"23.56M","Top 1 Accuracy":"75.9%"},"uses_additional_data":false,"paper_date":"2021-04-18","paper":"/paper/solving-inefficiency-of-self-supervised","paper_url":"https://arxiv.org/abs/2104.08760v3","paper_title":"Solving Inefficiency of Self-supervised Representation Learning","code":"https://github.com/wanggrun/triplet","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":66,"model":"MAE (ViT-L)","metrics":{"Number of Params":"306M","Top 1 Accuracy":"75.8%"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/masked-autoencoders-are-scalable-vision","paper_url":"https://arxiv.org/abs/2111.06377v2","paper_title":"Masked Autoencoders Are Scalable Vision Learners","code":"https://github.com/facebookresearch/mae","n_code_links":58,"syntology":{"n_ran":71,"n_unverified":66,"n_samples":137,"n_pointer_only_licence":73}},{"rank_in_archive_order":67,"model":"DnC (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"75.8%"},"uses_additional_data":false,"paper_date":"2021-05-17","paper":"/paper/divide-and-contrast-self-supervised-learning","paper_url":"https://arxiv.org/abs/2105.08054v1","paper_title":"Divide and Contrast: Self-supervised Learning from Uncurated Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":68,"model":"CaCo (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"75.7%"},"uses_additional_data":false,"paper_date":"2022-03-27","paper":"/paper/caco-both-positive-and-negative-samples-are","paper_url":"https://arxiv.org/abs/2203.14370v1","paper_title":"CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-adversarial Contrastive Learning","code":"https://github.com/maple-research-lab/caco","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":69,"model":"SimCLRv2 (ResNet-50 x2)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"75.6%","Top 5 Accuracy":"92.7%"},"uses_additional_data":false,"paper_date":"2020-06-17","paper":"/paper/big-self-supervised-models-are-strong-semi","paper_url":"https://arxiv.org/abs/2006.10029v2","paper_title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","code":"https://github.com/google-research/simclr","n_code_links":9,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":70,"model":"C-BYOL (ResNet-50, 1000 epochs)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"75.6%","Top 5 Accuracy":"92.7%"},"uses_additional_data":false,"paper_date":"2021-09-27","paper":"/paper/compressive-visual-representations","paper_url":"https://arxiv.org/abs/2109.12909v3","paper_title":"Compressive Visual Representations","code":"https://github.com/google-research/compressive-visual-representations","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":71,"model":"NNCLR (ResNet-50, multi-crop)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"75.6%","Top 5 Accuracy":"92.4"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/with-a-little-help-from-my-friends-nearest","paper_url":"https://arxiv.org/abs/2104.14548v2","paper_title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","code":"https://github.com/lightly-ai/lightly","n_code_links":4,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":72,"model":"HEXA","metrics":{"Number of Params":"24M","Top 1 Accuracy":"75.5%"},"uses_additional_data":false,"paper_date":"2020-12-25","paper":"/paper/self-supervised-pre-training-with-hard","paper_url":"https://arxiv.org/abs/2012.13493v2","paper_title":"Self-supervised Pre-training with Hard Examples Improves Visual Representations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":73,"model":"SCE (ResNet-50, multi-crop)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"75.4%"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/similarity-contrastive-estimation-for-self","paper_url":"https://arxiv.org/abs/2111.14585v2","paper_title":"Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning","code":"https://github.com/juliendenize/eztorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":74,"model":"SwAV (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"75.3%"},"uses_additional_data":false,"paper_date":"2020-06-17","paper":"/paper/unsupervised-learning-of-visual-features-by","paper_url":"https://arxiv.org/abs/2006.09882v5","paper_title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","code":"https://github.com/open-mmlab/mmdetection","n_code_links":18,"syntology":{"n_ran":13,"n_unverified":4,"n_samples":17,"n_pointer_only_licence":6}},{"rank_in_archive_order":75,"model":"DINO (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"75.3%"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/emerging-properties-in-self-supervised-vision","paper_url":"https://arxiv.org/abs/2104.14294v2","paper_title":"Emerging Properties in Self-Supervised Vision Transformers","code":"https://github.com/facebookresearch/dino","n_code_links":32,"syntology":{"n_ran":5,"n_unverified":15,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":76,"model":"InfoMin (ResNeXt-152)","metrics":{"Number of Params":"120M","Top 1 Accuracy":"75.2%"},"uses_additional_data":false,"paper_date":"2020-05-20","paper":"/paper/what-makes-for-good-views-for-contrastive","paper_url":"https://arxiv.org/abs/2005.10243v3","paper_title":"What Makes for Good Views for Contrastive Learning?","code":"https://github.com/HobbitLong/PyContrast","n_code_links":1,"syntology":null},{"rank_in_archive_order":77,"model":"DeepCluster-v2 (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"75.2%"},"uses_additional_data":false,"paper_date":"2020-06-17","paper":"/paper/unsupervised-learning-of-visual-features-by","paper_url":"https://arxiv.org/abs/2006.09882v5","paper_title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","code":"https://github.com/open-mmlab/mmdetection","n_code_links":18,"syntology":{"n_ran":13,"n_unverified":4,"n_samples":17,"n_pointer_only_licence":6}},{"rank_in_archive_order":78,"model":"Unicom (ViT-B/32)","metrics":{"Number of Params":"80M","Top 1 Accuracy":"75.0%"},"uses_additional_data":true,"paper_date":"2023-04-12","paper":"/paper/unicom-universal-and-compact-representation","paper_url":"https://arxiv.org/abs/2304.05884v1","paper_title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","code":"https://github.com/OML-Team/open-metric-learning","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":79,"model":"MoBY (Swin-T)","metrics":{"Number of Params":"29M","Top 1 Accuracy":"75%"},"uses_additional_data":false,"paper_date":"2021-05-10","paper":"/paper/self-supervised-learning-with-swin","paper_url":"https://arxiv.org/abs/2105.04553v2","paper_title":"Self-Supervised Learning with Swin Transformers","code":"https://github.com/microsoft/Swin-Transformer","n_code_links":6,"syntology":null},{"rank_in_archive_order":80,"model":"ReLIC (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"74.8%"},"uses_additional_data":false,"paper_date":"2020-10-15","paper":"/paper/representation-learning-via-invariant-causal-1","paper_url":"https://arxiv.org/abs/2010.07922v1","paper_title":"Representation Learning via Invariant Causal Mechanisms","code":"https://github.com/filipbasara0/relic","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":81,"model":"ReSSL(ResNet-50)  200ep","metrics":{"Number of Params":"24M","Top 1 Accuracy":"74.7%","Top 5 Accuracy":"92.3%"},"uses_additional_data":false,"paper_date":"2021-07-20","paper":"/paper/ressl-relational-self-supervised-learning","paper_url":"https://arxiv.org/abs/2107.09282v2","paper_title":"ReSSL: Relational Self-Supervised Learning with Weak Augmentation","code":"https://github.com/vturrisi/solo-learn","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":82,"model":"WCL (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"74.7%"},"uses_additional_data":false,"paper_date":"2021-10-10","paper":"/paper/weakly-supervised-contrastive-learning-1","paper_url":"https://arxiv.org/abs/2110.04770v1","paper_title":"Weakly Supervised Contrastive Learning","code":"https://github.com/KyleZheng1997/WCL","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":83,"model":"MV-MR","metrics":{"Top 1 Accuracy":"74.5%","Top 5 Accuracy":"92.1"},"uses_additional_data":false,"paper_date":"2023-03-21","paper":"/paper/mv-mr-multi-views-and-multi-representations","paper_url":"https://arxiv.org/abs/2303.12130v2","paper_title":"MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation","code":"https://github.com/vkinakh/mv-mr","n_code_links":1,"syntology":null},{"rank_in_archive_order":84,"model":"FNC (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"74.4%","Top 5 Accuracy":"91.8%"},"uses_additional_data":false,"paper_date":"2020-11-23","paper":"/paper/boosting-contrastive-self-supervised-learning","paper_url":"https://arxiv.org/abs/2011.11765v2","paper_title":"Boosting Contrastive Self-Supervised Learning with False Negative Cancellation","code":"https://github.com/google-research/fnc","n_code_links":1,"syntology":null},{"rank_in_archive_order":85,"model":"BYOL (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"74.3%","Top 5 Accuracy":"91.6%"},"uses_additional_data":false,"paper_date":"2020-06-13","paper":"/paper/bootstrap-your-own-latent-a-new-approach-to","paper_url":"https://arxiv.org/abs/2006.07733v3","paper_title":"Bootstrap your own latent: A new approach to self-supervised Learning","code":"https://github.com/deepmind/deepmind-research/tree/master/byol","n_code_links":31,"syntology":{"n_ran":62,"n_unverified":17,"n_samples":79,"n_pointer_only_licence":46}},{"rank_in_archive_order":86,"model":"SimCLR (ResNet-50 2x)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"74.2%","Top 5 Accuracy":"92.0%"},"uses_additional_data":false,"paper_date":"2020-02-13","paper":"/paper/a-simple-framework-for-contrastive-learning","paper_url":"https://arxiv.org/abs/2002.05709v3","paper_title":"A Simple Framework for Contrastive Learning of Visual Representations","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/simclr","n_code_links":96,"syntology":{"n_ran":79,"n_unverified":58,"n_samples":137,"n_pointer_only_licence":52}},{"rank_in_archive_order":87,"model":"Self-Classifier (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"74.2%"},"uses_additional_data":false,"paper_date":"2021-03-19","paper":"/paper/self-supervised-classification-network","paper_url":"https://arxiv.org/abs/2103.10994v3","paper_title":"Self-Supervised Classification Network","code":"https://github.com/elad-amrani/self-classifier","n_code_links":2,"syntology":null},{"rank_in_archive_order":88,"model":"GroCo (ResNet-50)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"73.9%","Top 5 Accuracy":"91.6"},"uses_additional_data":false,"paper_date":"2023-01-05","paper":"/paper/learning-by-sorting-self-supervised-learning","paper_url":"https://arxiv.org/abs/2301.02009v2","paper_title":"Learning by Sorting: Self-supervised Learning with Group Ordering Constraints","code":"https://github.com/ninatu/learning_by_sorting","n_code_links":1,"syntology":null},{"rank_in_archive_order":89,"model":"OBoW (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"73.8%","Top 5 Accuracy":"92.2%"},"uses_additional_data":false,"paper_date":"2020-12-21","paper":"/paper/online-bag-of-visual-words-generation-for","paper_url":"https://arxiv.org/abs/2012.11552v2","paper_title":"OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning","code":"https://github.com/valeoai/obow","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":90,"model":"VICReg (ResNet50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"73.2","Top 5 Accuracy":"91.1"},"uses_additional_data":false,"paper_date":"2021-05-11","paper":"/paper/vicreg-variance-invariance-covariance","paper_url":"https://arxiv.org/abs/2105.04906v3","paper_title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","code":"https://github.com/lightly-ai/lightly","n_code_links":6,"syntology":{"n_ran":11,"n_unverified":6,"n_samples":17,"n_pointer_only_licence":1}},{"rank_in_archive_order":91,"model":"Barlow Twins (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"73.2%","Top 5 Accuracy":"91"},"uses_additional_data":false,"paper_date":"2021-03-04","paper":"/paper/barlow-twins-self-supervised-learning-via","paper_url":"https://arxiv.org/abs/2103.03230v3","paper_title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","code":"https://github.com/lightly-ai/lightly","n_code_links":24,"syntology":{"n_ran":21,"n_unverified":5,"n_samples":26,"n_pointer_only_licence":10}},{"rank_in_archive_order":92,"model":"InfoMin (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"73.0%","Top 5 Accuracy":"91.1%"},"uses_additional_data":false,"paper_date":"2020-05-20","paper":"/paper/what-makes-for-good-views-for-contrastive","paper_url":"https://arxiv.org/abs/2005.10243v3","paper_title":"What Makes for Good Views for Contrastive Learning?","code":"https://github.com/HobbitLong/PyContrast","n_code_links":1,"syntology":null},{"rank_in_archive_order":93,"model":"DINO (ResMLP-24)","metrics":{"Number of Params":"30M","Top 1 Accuracy":"72.8%"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/resmlp-feedforward-networks-for-image","paper_url":"https://arxiv.org/abs/2105.03404v2","paper_title":"ResMLP: Feedforward networks for image classification with data-efficient training","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":94,"model":"MoBY (DeiT-S)","metrics":{"Number of Params":"22M","Top 1 Accuracy":"72.8%"},"uses_additional_data":false,"paper_date":"2021-05-10","paper":"/paper/self-supervised-learning-with-swin","paper_url":"https://arxiv.org/abs/2105.04553v2","paper_title":"Self-Supervised Learning with Swin Transformers","code":"https://github.com/microsoft/Swin-Transformer","n_code_links":6,"syntology":null},{"rank_in_archive_order":95,"model":"I-VNE+ (ResNet-50)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"72.1","Top 5 Accuracy":"91.0"},"uses_additional_data":false,"paper_date":"2023-04-04","paper":"/paper/vne-an-effective-method-for-improving-deep","paper_url":"https://arxiv.org/abs/2304.01434v1","paper_title":"VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution","code":"https://github.com/jaeill/CVPR23-VNE","n_code_links":1,"syntology":null},{"rank_in_archive_order":96,"model":"iGPT-XL (64x64, 15360 features)","metrics":{"Number of Params":"6801M","Top 1 Accuracy":"72.0%"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/generative-pretraining-from-pixels","paper_url":"https://openai.com/blog/image-gpt/","paper_title":"Generative Pretraining from Pixels","code":"https://github.com/openai/image-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":97,"model":"SimCLRv2 (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"71.7%","Top 5 Accuracy":"90.4%"},"uses_additional_data":false,"paper_date":"2020-06-17","paper":"/paper/big-self-supervised-models-are-strong-semi","paper_url":"https://arxiv.org/abs/2006.10029v2","paper_title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","code":"https://github.com/google-research/simclr","n_code_links":9,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":98,"model":"CPC v2 (ResNet-161) (arxiv v2)","metrics":{"Number of Params":"305M","Top 1 Accuracy":"71.5%","Top 5 Accuracy":"90.1%"},"uses_additional_data":false,"paper_date":"2019-05-22","paper":"/paper/data-efficient-image-recognition-with","paper_url":"https://arxiv.org/abs/1905.09272v3","paper_title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","code":"https://github.com/philip-bachman/amdim-public","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":99,"model":"SimSiam (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"71.3%"},"uses_additional_data":false,"paper_date":"2020-11-20","paper":"/paper/exploring-simple-siamese-representation","paper_url":"https://arxiv.org/abs/2011.10566v1","paper_title":"Exploring Simple Siamese Representation Learning","code":"https://github.com/lightly-ai/lightly","n_code_links":26,"syntology":{"n_ran":34,"n_unverified":5,"n_samples":39,"n_pointer_only_licence":22}},{"rank_in_archive_order":100,"model":"MoCo v2 (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"71.1%","Top 5 Accuracy":"90.1%"},"uses_additional_data":false,"paper_date":"2020-03-09","paper":"/paper/improved-baselines-with-momentum-contrastive","paper_url":"https://arxiv.org/abs/2003.04297v1","paper_title":"Improved Baselines with Momentum Contrastive Learning","code":"https://github.com/open-mmlab/mmdetection","n_code_links":36,"syntology":{"n_ran":8,"n_unverified":35,"n_samples":43,"n_pointer_only_licence":10}},{"rank_in_archive_order":101,"model":"SynCo (ResNet-50) 800ep","metrics":{"Number of Params":"24M","Top 1 Accuracy":"70.6%","Top 5 Accuracy":"89.8%"},"uses_additional_data":false,"paper_date":"2024-10-03","paper":"/paper/synco-synthetic-hard-negatives-in-contrastive","paper_url":"https://arxiv.org/abs/2410.02401v5","paper_title":"SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations","code":"https://github.com/giakoumoglou/synco","n_code_links":1,"syntology":null},{"rank_in_archive_order":102,"model":"CMC (ResNet-50 x2) (arxiv v5)","metrics":{"Number of Params":"188M","Top 1 Accuracy":"70.6%","Top 5 Accuracy":"89.7%"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/contrastive-multiview-coding","paper_url":"https://arxiv.org/abs/1906.05849v5","paper_title":"Contrastive Multiview Coding","code":"https://github.com/HobbitLong/PyContrast","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":103,"model":"SimCLR (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"69.3%","Top 5 Accuracy":"89.0%"},"uses_additional_data":false,"paper_date":"2020-02-13","paper":"/paper/a-simple-framework-for-contrastive-learning","paper_url":"https://arxiv.org/abs/2002.05709v3","paper_title":"A Simple Framework for Contrastive Learning of Visual Representations","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/simclr","n_code_links":96,"syntology":{"n_ran":79,"n_unverified":58,"n_samples":137,"n_pointer_only_licence":52}},{"rank_in_archive_order":104,"model":"iGPT-XL (64x64, 3072 features)","metrics":{"Number of Params":"6800M","Top 1 Accuracy":"68.7%"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/generative-pretraining-from-pixels","paper_url":"https://openai.com/blog/image-gpt/","paper_title":"Generative Pretraining from Pixels","code":"https://github.com/openai/image-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":105,"model":"MoCo (ResNet-50 4x)","metrics":{"Number of Params":"375M","Top 1 Accuracy":"68.6%"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/momentum-contrast-for-unsupervised-visual","paper_url":"https://arxiv.org/abs/1911.05722v3","paper_title":"Momentum Contrast for Unsupervised Visual Representation Learning","code":"https://github.com/open-mmlab/mmdetection","n_code_links":44,"syntology":{"n_ran":26,"n_unverified":16,"n_samples":42,"n_pointer_only_licence":16}},{"rank_in_archive_order":106,"model":"AMDIM (large) (arxiv v2)","metrics":{"Number of Params":"626M","Top 1 Accuracy":"68.1%"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/190600910","paper_url":"https://arxiv.org/abs/1906.00910v2","paper_title":"Learning Representations by Maximizing Mutual Information Across Views","code":"https://github.com/philip-bachman/amdim-public","n_code_links":3,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":107,"model":"MAE (ViT-B)","metrics":{"Number of Params":"80M","Top 1 Accuracy":"68.0%"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/masked-autoencoders-are-scalable-vision","paper_url":"https://arxiv.org/abs/2111.06377v2","paper_title":"Masked Autoencoders Are Scalable Vision Learners","code":"https://github.com/facebookresearch/mae","n_code_links":58,"syntology":{"n_ran":71,"n_unverified":66,"n_samples":137,"n_pointer_only_licence":73}},{"rank_in_archive_order":108,"model":"SynCo (ResNet-50) 200ep","metrics":{"Number of Params":"24M","Top 1 Accuracy":"67.9%","Top 5 Accuracy":"88"},"uses_additional_data":false,"paper_date":"2024-10-03","paper":"/paper/synco-synthetic-hard-negatives-in-contrastive","paper_url":"https://arxiv.org/abs/2410.02401v5","paper_title":"SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations","code":"https://github.com/giakoumoglou/synco","n_code_links":1,"syntology":null},{"rank_in_archive_order":109,"model":"DINO (ResMLP-12)","metrics":{"Number of Params":"15M","Top 1 Accuracy":"67.5%"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/resmlp-feedforward-networks-for-image","paper_url":"https://arxiv.org/abs/2105.03404v2","paper_title":"ResMLP: Feedforward networks for image classification with data-efficient training","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":110,"model":"CMC (ResNet-50) (arxiv v5)","metrics":{"Number of Params":"47M","Top 1 Accuracy":"66.2%","Top 5 Accuracy":"87.0%"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/contrastive-multiview-coding","paper_url":"https://arxiv.org/abs/1906.05849v5","paper_title":"Contrastive Multiview Coding","code":"https://github.com/HobbitLong/PyContrast","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":111,"model":"PCL (ResNet-50)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"65.9%"},"uses_additional_data":false,"paper_date":"2020-05-11","paper":"/paper/prototypical-contrastive-learning-of","paper_url":"https://arxiv.org/abs/2005.04966v5","paper_title":"Prototypical Contrastive Learning of Unsupervised Representations","code":"https://github.com/salesforce/PCL","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":112,"model":"MoCo (ResNet-50 2x)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"65.4%"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/momentum-contrast-for-unsupervised-visual","paper_url":"https://arxiv.org/abs/1911.05722v3","paper_title":"Momentum Contrast for Unsupervised Visual Representation Learning","code":"https://github.com/open-mmlab/mmdetection","n_code_links":44,"syntology":{"n_ran":26,"n_unverified":16,"n_samples":42,"n_pointer_only_licence":16}},{"rank_in_archive_order":113,"model":"iGPT-L (48x48)","metrics":{"Number of Params":"1400M","Top 1 Accuracy":"65.2%"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/generative-pretraining-from-pixels","paper_url":"https://openai.com/blog/image-gpt/","paper_title":"Generative Pretraining from Pixels","code":"https://github.com/openai/image-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":114,"model":"CMC (ResNet-101) (arxiv v3)","metrics":{"Top 1 Accuracy":"65.0%","Top 5 Accuracy":"86.0%"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/contrastive-multiview-coding","paper_url":"https://arxiv.org/abs/1906.05849v5","paper_title":"Contrastive Multiview Coding","code":"https://github.com/HobbitLong/PyContrast","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":115,"model":"CPC v2 (ResNet-50) (arxiv v2)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"63.8%","Top 5 Accuracy":"85.3%"},"uses_additional_data":false,"paper_date":"2019-05-22","paper":"/paper/data-efficient-image-recognition-with","paper_url":"https://arxiv.org/abs/1905.09272v3","paper_title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","code":"https://github.com/philip-bachman/amdim-public","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":116,"model":"MMCL (100 epoch, 256 batch size)","metrics":{"Top 1 Accuracy":"63.8%"},"uses_additional_data":false,"paper_date":"2021-12-21","paper":"/paper/max-margin-contrastive-learning","paper_url":"https://arxiv.org/abs/2112.11450v1","paper_title":"Max-Margin Contrastive Learning","code":"https://github.com/anshulbshah/MMCL","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":117,"model":"PIRL","metrics":{"Number of Params":"24M","Top 1 Accuracy":"63.6%"},"uses_additional_data":false,"paper_date":"2019-12-04","paper":"/paper/self-supervised-learning-of-pretext-invariant","paper_url":"https://arxiv.org/abs/1912.01991v1","paper_title":"Self-Supervised Learning of Pretext-Invariant Representations","code":"https://github.com/facebookresearch/vissl","n_code_links":7,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":118,"model":"AMDIM (small) (arxiv v2)","metrics":{"Number of Params":"194M","Top 1 Accuracy":"63.5%"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/190600910","paper_url":"https://arxiv.org/abs/1906.00910v2","paper_title":"Learning Representations by Maximizing Mutual Information Across Views","code":"https://github.com/philip-bachman/amdim-public","n_code_links":3,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":119,"model":"SeLa (ResNet50) (arxiv 3)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"61.5%","Top 5 Accuracy":"84.0%"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/self-labelling-via-simultaneous-clustering-1","paper_url":"https://arxiv.org/abs/1911.05371v3","paper_title":"Self-labelling via simultaneous clustering and representation learning","code":"https://github.com/yukimasano/self-label","n_code_links":5,"syntology":{"n_ran":7,"n_unverified":11,"n_samples":18,"n_pointer_only_licence":3}},{"rank_in_archive_order":120,"model":"BigBiGAN (RevNet-50 ×4, BN+CReLU)","metrics":{"Number of Params":"86M","Top 1 Accuracy":"61.3%","Top 5 Accuracy":"81.9%"},"uses_additional_data":false,"paper_date":"2019-07-04","paper":"/paper/large-scale-adversarial-representation","paper_url":"https://arxiv.org/abs/1907.02544v2","paper_title":"Large Scale Adversarial Representation Learning","code":"https://github.com/lukemelas/unsupervised-image-segmentation","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":121,"model":"CPC v2 (ResNet-161) (arxiv v1)","metrics":{"Number of Params":"305M","Top 1 Accuracy":"61.0%","Top 5 Accuracy":"83.0%"},"uses_additional_data":false,"paper_date":"2019-05-22","paper":"/paper/data-efficient-image-recognition-with","paper_url":"https://arxiv.org/abs/1905.09272v3","paper_title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","code":"https://github.com/philip-bachman/amdim-public","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":122,"model":"BigBiGAN (RevNet-50 ×4)","metrics":{"Number of Params":"86M","Top 1 Accuracy":"60.8%","Top 5 Accuracy":"81.4%"},"uses_additional_data":false,"paper_date":"2019-07-04","paper":"/paper/large-scale-adversarial-representation","paper_url":"https://arxiv.org/abs/1907.02544v2","paper_title":"Large Scale Adversarial Representation Learning","code":"https://github.com/lukemelas/unsupervised-image-segmentation","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":123,"model":"MoCo (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"60.6%"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/momentum-contrast-for-unsupervised-visual","paper_url":"https://arxiv.org/abs/1911.05722v3","paper_title":"Momentum Contrast for Unsupervised Visual Representation Learning","code":"https://github.com/open-mmlab/mmdetection","n_code_links":44,"syntology":{"n_ran":26,"n_unverified":16,"n_samples":42,"n_pointer_only_licence":16}},{"rank_in_archive_order":124,"model":"iGPT-L (32x32)","metrics":{"Number of Params":"1400M","Top 1 Accuracy":"60.3%"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/generative-pretraining-from-pixels","paper_url":"https://openai.com/blog/image-gpt/","paper_title":"Generative Pretraining from Pixels","code":"https://github.com/openai/image-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":125,"model":"AMDIM (arxiv v1)","metrics":{"Number of Params":"337M","Top 1 Accuracy":"60.2%"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/190600910","paper_url":"https://arxiv.org/abs/1906.00910v2","paper_title":"Learning Representations by Maximizing Mutual Information Across Views","code":"https://github.com/philip-bachman/amdim-public","n_code_links":3,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":126,"model":"LocalAgg (ResNet-50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"60.2%"},"uses_additional_data":false,"paper_date":"2019-03-29","paper":"/paper/local-aggregation-for-unsupervised-learning","paper_url":"http://arxiv.org/abs/1903.12355v2","paper_title":"Local Aggregation for Unsupervised Learning of Visual Embeddings","code":"https://github.com/neuroailab/LocalAggregation-Pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":127,"model":"CMC (ResNet-101)","metrics":{"Number of Params":"44M","Top 1 Accuracy":"60.1%","Top 5 Accuracy":"82.8%"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/contrastive-multiview-coding","paper_url":"https://arxiv.org/abs/1906.05849v5","paper_title":"Contrastive Multiview Coding","code":"https://github.com/HobbitLong/PyContrast","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":128,"model":"BigBiGAN (ResNet-50, BN+CReLU)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"56.6%","Top 5 Accuracy":"78.6%"},"uses_additional_data":false,"paper_date":"2019-07-04","paper":"/paper/large-scale-adversarial-representation","paper_url":"https://arxiv.org/abs/1907.02544v2","paper_title":"Large Scale Adversarial Representation Learning","code":"https://github.com/lukemelas/unsupervised-image-segmentation","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":129,"model":"SeLa (ResNet50)","metrics":{"Number of Params":"24M","Top 1 Accuracy":"55.7%","Top 5 Accuracy":"79.5%"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/self-labelling-via-simultaneous-clustering-1","paper_url":"https://arxiv.org/abs/1911.05371v3","paper_title":"Self-labelling via simultaneous clustering and representation learning","code":"https://github.com/yukimasano/self-label","n_code_links":5,"syntology":{"n_ran":7,"n_unverified":11,"n_samples":18,"n_pointer_only_licence":3}},{"rank_in_archive_order":130,"model":"Revisited Rotation (RevNet-50 ×4)","metrics":{"Number of Params":"86M","Top 1 Accuracy":"55.4%","Top 5 Accuracy":"77.9%"},"uses_additional_data":false,"paper_date":"2019-01-25","paper":"/paper/revisiting-self-supervised-visual","paper_url":"http://arxiv.org/abs/1901.09005v1","paper_title":"Revisiting Self-Supervised Visual Representation Learning","code":"https://github.com/philip-bachman/amdim-public","n_code_links":6,"syntology":{"n_ran":0,"n_unverified":15,"n_samples":15,"n_pointer_only_licence":7}},{"rank_in_archive_order":131,"model":"BigBiGAN (ResNet-50)","metrics":{"Number of Params":"25M","Top 1 Accuracy":"55.4%","Top 5 Accuracy":"77.4%"},"uses_additional_data":false,"paper_date":"2019-07-04","paper":"/paper/large-scale-adversarial-representation","paper_url":"https://arxiv.org/abs/1907.02544v2","paper_title":"Large Scale Adversarial Representation Learning","code":"https://github.com/lukemelas/unsupervised-image-segmentation","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":132,"model":"Revisited Rel.Patch.Loc (ResNet50 ×2)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"51.4%","Top 5 Accuracy":"74.0%"},"uses_additional_data":false,"paper_date":"2019-01-25","paper":"/paper/revisiting-self-supervised-visual","paper_url":"http://arxiv.org/abs/1901.09005v1","paper_title":"Revisiting Self-Supervised Visual Representation Learning","code":"https://github.com/philip-bachman/amdim-public","n_code_links":6,"syntology":{"n_ran":0,"n_unverified":15,"n_samples":15,"n_pointer_only_licence":7}},{"rank_in_archive_order":133,"model":"SeLa (AlexNet) (arxiv v3)","metrics":{"Number of Params":"61M","Top 1 Accuracy":"50.0%"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/self-labelling-via-simultaneous-clustering-1","paper_url":"https://arxiv.org/abs/1911.05371v3","paper_title":"Self-labelling via simultaneous clustering and representation learning","code":"https://github.com/yukimasano/self-label","n_code_links":5,"syntology":{"n_ran":7,"n_unverified":11,"n_samples":18,"n_pointer_only_licence":3}},{"rank_in_archive_order":134,"model":"CPC (ResNet-101 V2)","metrics":{"Number of Params":"44M","Top 1 Accuracy":"48.7%","Top 5 Accuracy":"73.6%"},"uses_additional_data":false,"paper_date":"2018-07-10","paper":"/paper/representation-learning-with-contrastive","paper_url":"http://arxiv.org/abs/1807.03748v2","paper_title":"Representation Learning with Contrastive Predictive Coding","code":"https://github.com/RElbers/info-nce-pytorch","n_code_links":28,"syntology":{"n_ran":29,"n_unverified":16,"n_samples":45,"n_pointer_only_licence":22}},{"rank_in_archive_order":135,"model":"Revisited Exemplar (ResNet-50 ×3)","metrics":{"Number of Params":"211M","Top 1 Accuracy":"46.0%","Top 5 Accuracy":"68.8%"},"uses_additional_data":false,"paper_date":"2019-01-25","paper":"/paper/revisiting-self-supervised-visual","paper_url":"http://arxiv.org/abs/1901.09005v1","paper_title":"Revisiting Self-Supervised Visual Representation Learning","code":"https://github.com/philip-bachman/amdim-public","n_code_links":6,"syntology":{"n_ran":0,"n_unverified":15,"n_samples":15,"n_pointer_only_licence":7}},{"rank_in_archive_order":136,"model":"Revisited Jigsaw (ResNet50 ×2)","metrics":{"Number of Params":"94M","Top 1 Accuracy":"44.6%","Top 5 Accuracy":"68.0%"},"uses_additional_data":false,"paper_date":"2019-01-25","paper":"/paper/revisiting-self-supervised-visual","paper_url":"http://arxiv.org/abs/1901.09005v1","paper_title":"Revisiting Self-Supervised Visual Representation Learning","code":"https://github.com/philip-bachman/amdim-public","n_code_links":6,"syntology":{"n_ran":0,"n_unverified":15,"n_samples":15,"n_pointer_only_licence":7}},{"rank_in_archive_order":137,"model":"CMC (Alexnet/2)","metrics":{"Number of Params":"30M","Top 1 Accuracy":"42.6%"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/contrastive-multiview-coding","paper_url":"https://arxiv.org/abs/1906.05849v5","paper_title":"Contrastive Multiview Coding","code":"https://github.com/HobbitLong/PyContrast","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":138,"model":"DeepCluster (AlexNet)","metrics":{"Number of Params":"61M","Top 1 Accuracy":"41.0"},"uses_additional_data":false,"paper_date":"2018-07-15","paper":"/paper/deep-clustering-for-unsupervised-learning-of","paper_url":"http://arxiv.org/abs/1807.05520v2","paper_title":"Deep Clustering for Unsupervised Learning of Visual Features","code":"https://github.com/facebookresearch/deepcluster","n_code_links":9,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":4}},{"rank_in_archive_order":139,"model":"Colorisation (improved) (ResNet-101)","metrics":{"Number of Params":"44M","Top 1 Accuracy":"39.6","Top 5 Accuracy":"62.5"},"uses_additional_data":false,"paper_date":"2017-08-25","paper":"/paper/multi-task-self-supervised-visual-learning","paper_url":"http://arxiv.org/abs/1708.07860v1","paper_title":"Multi-task Self-Supervised Visual Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":140,"model":"Rotation (AlexNet)","metrics":{"Number of Params":"86M","Top 1 Accuracy":"38.7"},"uses_additional_data":false,"paper_date":"2018-03-21","paper":"/paper/unsupervised-representation-learning-by-1","paper_url":"http://arxiv.org/abs/1803.07728v1","paper_title":"Unsupervised Representation Learning by Predicting Image Rotations","code":"https://github.com/facebookresearch/vissl","n_code_links":20,"syntology":{"n_ran":14,"n_unverified":8,"n_samples":22,"n_pointer_only_licence":18}},{"rank_in_archive_order":141,"model":"Split-Brain (AlexNet)","metrics":{"Number of Params":"61M","Top 1 Accuracy":"35.4%"},"uses_additional_data":false,"paper_date":"2016-11-29","paper":"/paper/split-brain-autoencoders-unsupervised","paper_url":"http://arxiv.org/abs/1611.09842v3","paper_title":"Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction","code":"https://github.com/richzhang/splitbrainauto","n_code_links":2,"syntology":null},{"rank_in_archive_order":142,"model":"Counting (AlexNet)","metrics":{"Number of Params":"61M","Top 1 Accuracy":"34.3"},"uses_additional_data":false,"paper_date":"2017-08-22","paper":"/paper/representation-learning-by-learning-to-count","paper_url":"http://arxiv.org/abs/1708.06734v1","paper_title":"Representation Learning by Learning to Count","code":"https://github.com/clvrai/representation-learning-by-learning-to-count","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":143,"model":"Colorization (AlexNet)","metrics":{"Number of Params":"61M","Top 1 Accuracy":"32.6%"},"uses_additional_data":false,"paper_date":"2016-03-28","paper":"/paper/colorful-image-colorization","paper_url":"http://arxiv.org/abs/1603.08511v5","paper_title":"Colorful Image Colorization","code":"https://github.com/richzhang/colorization","n_code_links":39,"syntology":{"n_ran":32,"n_unverified":41,"n_samples":73,"n_pointer_only_licence":41}},{"rank_in_archive_order":144,"model":"Multi-task SSL (ResNet-101)","metrics":{"Number of Params":"44M","Top 5 Accuracy":"70.2"},"uses_additional_data":false,"paper_date":"2017-08-25","paper":"/paper/multi-task-self-supervised-visual-learning","paper_url":"http://arxiv.org/abs/1708.07860v1","paper_title":"Multi-task Self-Supervised Visual Learning","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":109,"rows_with_any_sample_ran":83,"distinct_papers_with_graph_line":48,"distinct_papers_with_any_sample_ran":39,"samples_over_distinct_papers":{"n_ran":502,"n_unverified":459,"n_samples":961,"n_pointer_only_licence":377,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1263,"n_unverified":1186,"n_samples":2449,"n_pointer_only_licence":930,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}