{"url":"/sota/image-classification-on-tiny-imagenet-1","task":{"name":"Image Classification","url":"/task/image-classification","note":null},"dataset":{"name":"Tiny ImageNet Classification","url":"/dataset/tiny-imagenet"},"category":"Computer Vision","categories":["Adversarial","Computer Vision"],"category_note":null,"description":"**Image Classification** is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike [object detection](/task/object-detection), which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as [image retrieval](/task/image-retrieval), which also involves finding similar images in a large database.\r\n\r\n\r\n<span class=\"description-source\">Source: [Metamorphic Testing for Object Detection Systems ](https://arxiv.org/abs/1912.12162)</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":["Validation Acc"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Validation Acc":"higher"}},"counts":{"rows":23,"rows_with_code":20,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":5},"rows":[{"rank_in_archive_order":1,"model":"Astroformer","metrics":{"Validation Acc":"92.98"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/astroformer-more-data-might-not-be-all-you","paper_url":"https://arxiv.org/abs/2304.05350v2","paper_title":"Astroformer: More Data Might not be all you need for Classification","code":"https://github.com/Rishit-dagli/Astroformer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"DeiT-B/16-D + OCD(5)","metrics":{"Validation Acc":"92.0%"},"uses_additional_data":false,"paper_date":"2022-10-02","paper":"/paper/ocd-learning-to-overfit-with-conditional","paper_url":"https://arxiv.org/abs/2210.00471v5","paper_title":"OCD: Learning to Overfit with Conditional Diffusion Models","code":"https://github.com/shaharlutatipersonal/ocd","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"SwinV2-B + GradMatch","metrics":{"Validation Acc":"91.90"},"uses_additional_data":false,"paper_date":"2023-03-03","paper":"/paper/data-efficient-training-of-cnns-and","paper_url":"https://arxiv.org/abs/2303.02095v2","paper_title":"Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective","code":"https://github.com/transmuteai/data-efficient-transformers","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Swin-L","metrics":{"Validation Acc":"91.35%"},"uses_additional_data":true,"paper_date":"2022-05-21","paper":"/paper/vision-transformers-in-2022-an-update-on-tiny","paper_url":"https://arxiv.org/abs/2205.10660v1","paper_title":"Vision Transformers in 2022: An Update on Tiny ImageNet","code":"https://github.com/ehuynh1106/TinyImageNet-Transformers","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"DeiT-B/16 (PUGD)","metrics":{"Validation Acc":"91.02%"},"uses_additional_data":true,"paper_date":"2021-10-01","paper":"/paper/update-in-unit-gradient","paper_url":"https://arxiv.org/abs/2110.00199v2","paper_title":"Perturbated Gradients Updating within Unit Space for Deep Learning","code":"https://github.com/hanktseng131415go/pugd","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DeiT-B/16-D + OCD","metrics":{"Validation Acc":"90.8%"},"uses_additional_data":false,"paper_date":"2022-10-02","paper":"/paper/ocd-learning-to-overfit-with-conditional","paper_url":"https://arxiv.org/abs/2210.00471v5","paper_title":"OCD: Learning to Overfit with Conditional Diffusion Models","code":"https://github.com/shaharlutatipersonal/ocd","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"ViT-B/16 (PUGD)","metrics":{"Validation Acc":"90.74%"},"uses_additional_data":true,"paper_date":"2021-10-01","paper":"/paper/update-in-unit-gradient","paper_url":"https://arxiv.org/abs/2110.00199v2","paper_title":"Perturbated Gradients Updating within Unit Space for Deep Learning","code":"https://github.com/hanktseng131415go/pugd","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"MANO-tiny","metrics":{"Validation Acc":"87.52"},"uses_additional_data":true,"paper_date":"2025-07-03","paper":"/paper/linear-attention-with-global-context-a-1","paper_url":"https://arxiv.org/abs/2507.02748v1","paper_title":"Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics","code":"https://github.com/AlexColagrande/MANO","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"EfficientNet-B1+DCL","metrics":{"Validation Acc":"84.39%"},"uses_additional_data":true,"paper_date":"2019-12-17","paper":"/paper/direction-concentration-learning-enhancing","paper_url":"https://arxiv.org/abs/1912.08136v2","paper_title":"Direction Concentration Learning: Enhancing Congruency in Machine Learning","code":"https://github.com/luoyan407/congruency","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":10,"model":"WaveMixLite-144/7","metrics":{"Validation Acc":"77.47%"},"uses_additional_data":false,"paper_date":"2022-05-28","paper":"/paper/wavemix-lite-a-resource-efficient-neural","paper_url":"https://arxiv.org/abs/2205.14375v5","paper_title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","code":"https://github.com/pranavphoenix/WaveMix","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"Context-Aware Pipeline","metrics":{"Validation Acc":"73.6%"},"uses_additional_data":false,"paper_date":"2021-12-30","paper":"/paper/context-aware-compilation-of-dnn-training","paper_url":"https://dl.acm.org/doi/abs/10.1145/3494981","paper_title":"Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud","code":"https://github.com/dixiyao/Context-Aware-Compilation-of-DNN-Training-Pipelines-across-Edge-and-Cloud","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"ResNeXt-50 (SAMix+DM)","metrics":{"Validation Acc":"72.39"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"ResNeXt-50 (SAMix)","metrics":{"Validation Acc":"72.18%"},"uses_additional_data":false,"paper_date":"2021-11-30","paper":"/paper/boosting-discriminative-visual-representation","paper_url":"https://arxiv.org/abs/2111.15454v3","paper_title":"Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup","code":"https://github.com/Westlake-AI/openmixup","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"ResNeXt-50 (AutoMix+DM)","metrics":{"Validation Acc":"71.56"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"ResNeXt-50 (AutoMix)","metrics":{"Validation Acc":"70.72%"},"uses_additional_data":false,"paper_date":"2021-03-24","paper":"/paper/automix-unveiling-the-power-of-mixup","paper_url":"https://arxiv.org/abs/2103.13027v6","paper_title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","code":"https://github.com/Westlake-AI/openmixup","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"PreActResNet-18-3","metrics":{"Validation Acc":"70.24%"},"uses_additional_data":false,"paper_date":"2021-03-10","paper":"/paper/mixmo-mixing-multiple-inputs-for-multiple","paper_url":"https://arxiv.org/abs/2103.06132v3","paper_title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","code":"https://github.com/alexrame/mixmo-pytorch","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"ResNet18 (SAMix)","metrics":{"Validation Acc":"68.89%"},"uses_additional_data":false,"paper_date":"2021-11-30","paper":"/paper/boosting-discriminative-visual-representation","paper_url":"https://arxiv.org/abs/2111.15454v3","paper_title":"Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup","code":"https://github.com/Westlake-AI/openmixup","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"ResNeXt-50 (PuzzleMix+DM)","metrics":{"Validation Acc":"68.04"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"UPANets","metrics":{"Validation Acc":"67.67"},"uses_additional_data":false,"paper_date":"2021-03-15","paper":"/paper/upanets-learning-from-the-universal-pixel","paper_url":"https://arxiv.org/abs/2103.08640v2","paper_title":"UPANets: Learning from the Universal Pixel Attention Networks","code":"https://github.com/hanktseng131415go/UPANets","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"ResNet18 (AutoMix)","metrics":{"Validation Acc":"67.33%"},"uses_additional_data":false,"paper_date":"2021-03-24","paper":"/paper/automix-unveiling-the-power-of-mixup","paper_url":"https://arxiv.org/abs/2103.13027v6","paper_title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","code":"https://github.com/Westlake-AI/openmixup","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"DenseNet + Residual Networks","metrics":{"Validation Acc":"60%"},"uses_additional_data":false,"paper_date":"2019-04-23","paper":"/paper/densenet-models-for-tiny-imagenet","paper_url":"https://arxiv.org/abs/1904.10429v2","paper_title":"DenseNet Models for Tiny ImageNet Classification","code":"https://github.com/ZohebAbai/Tiny-ImageNet-Challenge","n_code_links":3,"syntology":null},{"rank_in_archive_order":22,"model":"WaveMixLite-160/13","metrics":{"Validation Acc":"54.76"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/wavemix-lite-a-resource-efficient-neural-1","paper_url":"https://openreview.net/forum?id=y_icnxeeUcl","paper_title":"WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis","code":"https://github.com/pranavphoenix/WaveMix","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"Convolutional Nystromformer for Vision (CNV)","metrics":{"Validation Acc":"49.56"},"uses_additional_data":false,"paper_date":"2022-01-25","paper":"/paper/convolutional-xformers-for-vision","paper_url":"https://arxiv.org/abs/2201.10271v1","paper_title":"Convolutional Xformers for Vision","code":"https://github.com/pranavphoenix/cxv","n_code_links":1,"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":8,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":10,"n_unverified":9,"n_samples":19,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":14,"n_unverified":13,"n_samples":27,"n_pointer_only_licence":5,"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"}}}