{"url":"/dataset/oxford-102-flower","name":"Oxford 102 Flower","full_name":"102 Category Flower Dataset","description_markdown":"**Oxford 102 Flower** is an image classification dataset consisting of 102 flower categories. The flowers chosen to be flower commonly occurring in the United Kingdom. Each class consists of between 40 and 258 images.\r\n\r\nThe images have large scale, pose and light variations. In addition, there are categories that have large variations within the category and several very similar categories.","description_withheld":null,"homepage":"https://www.robots.ox.ac.uk/~vgg/data/flowers/102/","introduced_date":"2008-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/automated-flower-classification-over-a-large","title":"Automated Flower Classification over a Large Number of Classes","first_author":"Maria-Elena Nilsback","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-learning"},{"name":"Few-Shot Image Classification","url":"/task/few-shot-image-classification","datasets_with_task":"/datasets/task/few-shot-image-classification"},{"name":"Few-Shot Learning","url":"/task/few-shot-learning","datasets_with_task":"/datasets/task/few-shot-learning"},{"name":"Continual Learning","url":"/task/continual-learning","datasets_with_task":"/datasets/task/continual-learning"},{"name":"Image Clustering","url":"/task/image-clustering","datasets_with_task":"/datasets/task/image-clustering"},{"name":"Fine-Grained Image Classification","url":"/task/fine-grained-image-classification","datasets_with_task":"/datasets/task/fine-grained-image-classification"},{"name":"Neural Architecture Search","url":"/task/architecture-search","datasets_with_task":"/datasets/task/architecture-search"},{"name":"Transductive Zero-Shot Classification","url":"/task/transductive-zero-shot-classification","datasets_with_task":"/datasets/task/transductive-zero-shot-classification"},{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"},{"name":"Prompt Engineering","url":"/task/prompt-engineering","datasets_with_task":"/datasets/task/prompt-engineering"},{"name":"Generalized Zero-Shot Learning","url":"/task/generalized-zero-shot-learning","datasets_with_task":"/datasets/task/generalized-zero-shot-learning"},{"name":"Few-Shot Learning - 4 shots","url":"/task/few-shot-learning-4-shots","datasets_with_task":"/datasets/task/few-shot-learning-4-shots"},{"name":"Point-interactive Image Colorization","url":"/task/point-interactive-image-colorization","datasets_with_task":"/datasets/task/point-interactive-image-colorization"},{"name":"Unsupervised Image Segmentation","url":"/task/unsupervised-image-segmentation","datasets_with_task":"/datasets/task/unsupervised-image-segmentation"}],"languages":[],"variants":["Oxford 102 Flowers","Flowers-102","Oxford 102 Flowers 256 x 256","Flowers-102 - 0-Shot","Flowers (Fine-grained 6 Tasks)","Flowers","Oxford 102 Flower"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.Flowers102.html","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/oxford_flowers102","frameworks":["tf","jax"]},{"repo":"https://github.com/Graviti-AI/datasets","url":"https://gas.graviti.com/dataset/hellodataset/Flower102-1","frameworks":["tf","pytorch"]}],"num_papers_in_archive":1307,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset_variant":"Flowers-102","rows":52,"metrics":["Accuracy","FLOPS","PARAMS","Per-Class Accuracy"],"first_row_in_archive_order":{"model":"CCT-14/7x2","paper":"/paper/escaping-the-big-data-paradigm-with-compact","metrics":{"Accuracy":"99.76"},"code_links":[{"title":"keras-team/keras-io","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/cct.py"},{"title":"SHI-Labs/Compact-Transformers","url":"https://github.com/SHI-Labs/Compact-Transformers"},{"title":"brohrer/sharpened-cosine-similarity","url":"https://github.com/brohrer/sharpened-cosine-similarity"},{"title":"rishikksh20/compact-convolution-transformer","url":"https://github.com/rishikksh20/compact-convolution-transformer"},{"title":"Shreyas-Bhat/CompactTransformers","url":"https://github.com/Shreyas-Bhat/CompactTransformers"},{"title":"stevenwalton/scs-cct","url":"https://github.com/stevenwalton/scs-cct"},{"title":"ahmedelmahy/myownvit","url":"https://github.com/ahmedelmahy/myownvit"},{"title":"Ryul0rd/compact-convolutional-transformer","url":"https://github.com/Ryul0rd/compact-convolutional-transformer"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/cct"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford","task":"Fine-Grained Image Classification","dataset_variant":"Oxford 102 Flowers","rows":25,"metrics":["Accuracy","Top-1 Error Rate","FLOPS","PARAMS","Top 1 Accuracy"],"first_row_in_archive_order":{"model":"IELT","paper":"/paper/fine-grained-visual-classification-via-2","metrics":{"Accuracy":"99.64%"},"code_links":[{"title":"mobulan/ielt","url":"https://github.com/mobulan/ielt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/prompt-engineering-on-oxford-102-flower","task":"Prompt Engineering","dataset_variant":"Oxford 102 Flower","rows":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper":"/paper/promptkd-unsupervised-prompt-distillation-for","metrics":{"Harmonic mean":"90.24"},"code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-to-image-generation-on-oxford-102","task":"Text-to-Image Generation","dataset_variant":"Oxford 102 Flowers","rows":8,"metrics":["FID","Inception score"],"first_row_in_archive_order":{"model":"RAT-Diffusion","paper":"/paper/data-extrapolation-for-text-to-image","metrics":{"FID":"9.52","Inception score":"4.35"},"code_links":[{"title":"senmaoy/RAT-Diffusion","url":"https://github.com/senmaoy/RAT-Diffusion"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/point-interactive-image-colorization-on-1","task":"Point-interactive Image Colorization","dataset_variant":"Oxford 102 Flowers","rows":7,"metrics":["PSNR@10","PSNR@1","PSNR@100"],"first_row_in_archive_order":{"model":"iColoriT","paper":"/paper/icolorit-towards-propagating-local-hint-to","metrics":{"PSNR@1":"22.925","PSNR@10":"27.37","PSNR@100":"30.731"},"code_links":[{"title":"pmh9960/iColoriT","url":"https://github.com/pmh9960/iColoriT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/continual-learning-on-flowers-fine-grained-6","task":"Continual Learning","dataset_variant":"Flowers (Fine-grained 6 Tasks)","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CondConvContinual","paper":"/paper/extending-conditional-convolution-structures","metrics":{"Accuracy":"97.16"},"code_links":[{"title":"ivclab/CondConvContinual","url":"https://github.com/ivclab/CondConvContinual"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/neural-architecture-search-on-oxford-102","task":"Neural Architecture Search","dataset_variant":"Oxford 102 Flowers","rows":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper":"/paper/neural-architecture-transfer","metrics":{"Accuracy (%)":"98.3","FLOPS":"400M","PARAMS":"4.2M"},"code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/generalized-zero-shot-learning-on-oxford-102-1","task":"Generalized Zero-Shot Learning","dataset_variant":"Oxford 102 Flower","rows":2,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"SPOT (FREE)","paper":"/paper/synthetic-sample-selection-for-generalized","metrics":{"Harmonic mean":"75.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-oxford-102-flowers-256-x","task":"Image Generation","dataset_variant":"Oxford 102 Flowers 256 x 256","rows":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"Projected GAN","paper":"/paper/projected-gans-converge-faster","metrics":{"FID":"3.86"},"code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-learning-on-flowers-102","task":"Zero-Shot Learning","dataset_variant":"Flowers-102","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZLaP","paper":"/paper/label-propagation-for-zero-shot","metrics":{"Accuracy":"75.9"},"code_links":[{"title":"vladan-stojnic/zlap","url":"https://github.com/vladan-stojnic/zlap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-learning-on-oxford-102-flower","task":"Zero-Shot Learning","dataset_variant":"Oxford 102 Flower","rows":2,"metrics":["average top-1 classification accuracy"],"first_row_in_archive_order":{"model":"SPOT","paper":"/paper/synthetic-sample-selection-for-generalized","metrics":{"average top-1 classification accuracy":"71.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-flowers-102-1","task":"Few-Shot Image Classification","dataset_variant":"Flowers-102 - 0-Shot","rows":1,"metrics":["AP50","Accuracy"],"first_row_in_archive_order":{"model":"Word CNN-RNN (DS-SJE Embedding)","paper":"/paper/learning-deep-representations-of-fine-grained","metrics":{"AP50":"59.6","Accuracy":"65.6%"},"code_links":[{"title":"hanzhanggit/StackGAN-v2","url":"https://github.com/hanzhanggit/StackGAN-v2"},{"title":"reedscot/cvpr2016","url":"https://github.com/reedscot/cvpr2016"},{"title":"hanzhanggit/StackGAN-inception-model","url":"https://github.com/hanzhanggit/StackGAN-inception-model"},{"title":"Vishal-V/StackGAN","url":"https://github.com/Vishal-V/StackGAN"},{"title":"rightlit/StackGAN-v2-rev","url":"https://github.com/rightlit/StackGAN-v2-rev"},{"title":"priscillalui/StackGAN-Stories","url":"https://github.com/priscillalui/StackGAN-Stories"},{"title":"Maymaher/StackGANv2","url":"https://github.com/Maymaher/StackGANv2"},{"title":"rafiahmed40/stack-adverserial-network","url":"https://github.com/rafiahmed40/stack-adverserial-network"},{"title":"Vigneshthanga/stackGAN-v2","url":"https://github.com/Vigneshthanga/stackGAN-v2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-oxford-102","task":"Few-Shot Image Classification","dataset_variant":"Oxford 102 Flower","rows":1,"metrics":["ACCURACY"],"first_row_in_archive_order":{"model":"RS-FSL","paper":"/paper/rich-semantics-improve-few-shot-learning","metrics":{"ACCURACY":"75.33"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-learning-on-flowers-102","task":"Few-Shot Learning","dataset_variant":"Flowers-102","rows":1,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"Variational Prompt Tuning","paper":"/paper/variational-prompt-tuning-improves","metrics":{"Harmonic mean":"81.12"},"code_links":[{"title":"saic-fi/bayesian-prompt-learning","url":"https://github.com/saic-fi/bayesian-prompt-learning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-clustering-on-flowers-102","task":"Image Clustering","dataset_variant":"Flowers-102","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TURTLE (CLIP + DINOv2)","paper":"/paper/let-go-of-your-labels-with-unsupervised-1","metrics":{"Accuracy":"99.6"},"code_links":[{"title":"mlbio-epfl/turtle","url":"https://github.com/mlbio-epfl/turtle"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/transductive-zero-shot-classification-on-2","task":"Transductive Zero-Shot Classification","dataset_variant":"Flowers-102","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZLaP","paper":"/paper/label-propagation-for-zero-shot","metrics":{"Accuracy":"73.4"},"code_links":[{"title":"vladan-stojnic/zlap","url":"https://github.com/vladan-stojnic/zlap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/linear-attention-with-global-context-a-1","title":"Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics","date":"2025-07-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmrl-parameter-efficient-and-interaction","title":"MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models","date":"2025-05-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmrl-multi-modal-representation-learning-for","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","date":"2025-03-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/data-extrapolation-for-text-to-image","title":"Data Extrapolation for Text-to-image Generation on Small Datasets","date":"2024-10-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hpt-hierarchically-prompting-vision-language","title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","date":"2024-08-27","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/let-go-of-your-labels-with-unsupervised-1","title":"Let Go of Your Labels with Unsupervised Transfer","date":"2024-06-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/label-propagation-for-zero-shot","title":"Label Propagation for Zero-shot Classification with Vision-Language Models","date":"2024-04-05","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/prompt-learning-via-meta-regularization","title":"Prompt Learning via Meta-Regularization","date":"2024-04-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/promptkd-unsupervised-prompt-distillation-for","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","date":"2024-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dept-decoupled-prompt-tuning","title":"DePT: Decoupled Prompt Tuning","date":"2023-09-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/read-only-prompt-optimization-for-vision","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","date":"2023-08-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-regulating-prompts-foundational-model","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","date":"2023-07-13","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":7,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/consistency-guided-prompt-learning-for-vision","title":"Consistency-guided Prompt Learning for Vision-Language Models","date":"2023-06-01","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reduction-of-class-activation-uncertainty","title":"Reduction of Class Activation Uncertainty with Background Information","date":"2023-05-05","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/synthetic-sample-selection-for-generalized","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","date":"2023-04-06","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/your-diffusion-model-is-secretly-a-zero-shot","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","date":"2023-03-28","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fine-grained-visual-classification-via-2","title":"Fine-Grained Visual Classification via Internal Ensemble Learning Transformer","date":"2023-02-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-domain-invariant-prompt-for-vision","title":"Learning Domain Invariant Prompt for Vision-Language Models","date":"2022-12-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/helpful-or-harmful-inter-task-association-in","title":"Helpful or Harmful: Inter-Task Association in Continual Learning","date":"2022-10-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/variational-prompt-tuning-improves","title":"Bayesian Prompt Learning for Image-Language Model Generalization","date":"2022-10-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sr-gnn-spatial-relation-aware-graph-neural","title":"SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization","date":"2022-09-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/icolorit-towards-propagating-local-hint-to","title":"iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer","date":"2022-07-14","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/transboost-improving-the-best-imagenet","title":"TransBoost: Improving the Best ImageNet Performance using Deep Transduction","date":"2022-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/an-evolutionary-approach-to-dynamic","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","date":"2022-05-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/recurrent-affine-transformation-for-text-to","title":"Recurrent Affine Transformation for Text-to-image Synthesis","date":"2022-04-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/three-things-everyone-should-know-about","title":"Three things everyone should know about Vision Transformers","date":"2022-03-18","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bamboo-building-mega-scale-vision-dataset","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","date":"2022-03-15","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/conditional-prompt-learning-for-vision","title":"Conditional Prompt Learning for Vision-Language Models","date":"2022-03-10","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vision-models-are-more-robust-and-fair-when","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","date":"2022-02-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vector-quantized-diffusion-model-for-text-to","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","date":"2021-11-29","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/projected-gans-converge-faster","title":"Projected GANs Converge Faster","date":"2021-11-01","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":49,"samples_ran":38,"samples_unverified":11,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-comprehensive-study-on-torchvision-pre","title":"A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification","date":"2021-10-14","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/resnet-strikes-back-an-improved-training","title":"ResNet strikes back: An improved training procedure in timm","date":"2021-10-01","rows_on_this_dataset":2,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/convmlp-hierarchical-convolutional-mlps-for","title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","date":"2021-09-09","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/global-filter-networks-for-image","title":"Global Filter Networks for Image Classification","date":"2021-07-01","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/autoformer-searching-transformers-for-visual","title":"AutoFormer: Searching Transformers for Visual Recognition","date":"2021-07-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/when-vision-transformers-outperform-resnets","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","date":"2021-06-03","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/effect-of-large-scale-pre-training-on-full","title":"Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images","date":"2021-05-31","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/resmlp-feedforward-networks-for-image","title":"ResMLP: Feedforward networks for image classification with data-efficient training","date":"2021-05-07","rows_on_this_dataset":4,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/with-a-little-help-from-my-friends-nearest","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","date":"2021-04-29","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rich-semantics-improve-few-shot-learning","title":"Rich Semantics Improve Few-shot Learning","date":"2021-04-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/escaping-the-big-data-paradigm-with-compact","title":"Escaping the Big Data Paradigm with Compact Transformers","date":"2021-04-12","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","rows_on_this_dataset":4,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":30,"samples_ran":23,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficientnetv2-smaller-models-and-faster","title":"EfficientNetV2: Smaller Models and Faster Training","date":"2021-04-01","rows_on_this_dataset":3,"code_links":26,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":79,"samples_ran":41,"samples_unverified":38,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/going-deeper-with-image-transformers","title":"Going deeper with Image Transformers","date":"2021-03-31","rows_on_this_dataset":1,"code_links":21,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cvt-introducing-convolutions-to-vision","title":"CvT: Introducing Convolutions to Vision Transformers","date":"2021-03-29","rows_on_this_dataset":1,"code_links":16,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":47,"samples_ran":29,"samples_unverified":18,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/incorporating-convolution-designs-into-visual","title":"Incorporating Convolution Designs into Visual Transformers","date":"2021-03-22","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":16,"samples_unverified":8,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","rows_on_this_dataset":1,"code_links":82,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":16,"samples_unverified":4,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":8,"samples_unverified":2,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","rows_on_this_dataset":2,"code_links":40,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":12,"samples_unverified":7,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/extending-conditional-convolution-structures","title":"EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING","date":"2020-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/grafit-learning-fine-grained-image","title":"Grafit: Learning fine-grained image representations with coarse labels","date":"2020-11-25","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","rows_on_this_dataset":1,"code_links":158,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":419,"samples_ran":281,"samples_unverified":138,"pointer_only_for_licence":154,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/domain-adaptive-transfer-learning-on-visual","title":"Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization","date":"2020-10-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sharpness-aware-minimization-for-efficiently-1","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","date":"2020-10-03","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":8,"samples_unverified":12,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spinalnet-deep-neural-network-with-gradual-1","title":"SpinalNet: Deep Neural Network with Gradual Input","date":"2020-07-07","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/instance-aware-image-colorization","title":"Instance-aware Image Colorization","date":"2020-05-21","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-architecture-transfer","title":"Neural Architecture Transfer","date":"2020-05-12","rows_on_this_dataset":12,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tresnet-high-performance-gpu-dedicated","title":"TResNet: High Performance GPU-Dedicated Architecture","date":"2020-03-30","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/latent-embedding-feedback-and-discriminative","title":"Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification","date":"2020-03-17","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/compounding-the-performance-improvements-of","title":"Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network","date":"2020-01-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/large-scale-learning-of-general-visual","title":"Big Transfer (BiT): General Visual Representation Learning","date":"2019-12-24","rows_on_this_dataset":4,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/compacting-picking-and-growing-for","title":"Compacting, Picking and Growing for Unforgetting Continual Learning","date":"2019-10-15","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/classification-specific-parts-for-improving","title":"Classification-Specific Parts for Improving Fine-Grained Visual Categorization","date":"2019-09-16","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/fixing-the-train-test-resolution-discrepancy","title":"Fixing the train-test resolution discrepancy","date":"2019-06-14","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","rows_on_this_dataset":1,"code_links":144,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":302,"samples_ran":171,"samples_unverified":131,"pointer_only_for_licence":112,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/side-window-filtering","title":"Side Window Filtering","date":"2019-05-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/msg-gan-multi-scale-gradients-gan-for-more","title":"MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks","date":"2019-03-14","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":3,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/autoaugment-learning-augmentation-policies","title":"AutoAugment: Learning Augmentation Policies from Data","date":"2018-05-24","rows_on_this_dataset":1,"code_links":33,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":43,"samples_ran":6,"samples_unverified":37,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/piggyback-adapting-a-single-network-to","title":"Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights","date":"2018-01-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/packnet-adding-multiple-tasks-to-a-single","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","date":"2017-11-15","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stackgan-realistic-image-synthesis-with","title":"StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks","date":"2017-10-19","rows_on_this_dataset":2,"code_links":16,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":10,"samples_unverified":21,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pairwise-confusion-for-fine-grained-visual","title":"Pairwise Confusion for Fine-Grained Visual Classification","date":"2017-05-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-time-user-guided-image-colorization-with","title":"Real-Time User-Guided Image Colorization with Learned Deep Priors","date":"2017-05-08","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/stackgan-text-to-photo-realistic-image","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","date":"2016-12-10","rows_on_this_dataset":1,"code_links":21,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":11,"samples_unverified":20,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/progressive-neural-networks","title":"Progressive Neural Networks","date":"2016-06-15","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-deep-representations-of-fine-grained","title":"Learning Deep Representations of Fine-grained Visual Descriptions","date":"2016-05-17","rows_on_this_dataset":1,"code_links":9,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":47,"samples_harvested":1325,"samples_ran":757,"samples_unverified":568,"pointer_only_for_licence":359,"papers_with_no_sample_that_ran":7,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}