{"url":"/dataset/stanford-dogs","name":"Stanford Dogs","full_name":"Stanford Dogs","description_markdown":"The **Stanford Dogs** dataset contains 20,580 images of 120 classes of dogs from around the world, which are divided into 12,000 images for training and 8,580 images for testing.\n\nSource: [Universal-to-Specific Framework for Complex Action Recognition](https://arxiv.org/abs/2007.06149)\nImage Source: [https://www.tensorflow.org/datasets/catalog/stanford_dogs](https://www.tensorflow.org/datasets/catalog/stanford_dogs)","description_withheld":null,"homepage":"http://vision.stanford.edu/aditya86/ImageNetDogs/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Few-Shot Image Classification","url":"/task/few-shot-image-classification","datasets_with_task":"/datasets/task/few-shot-image-classification"},{"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":"Fine-Grained Visual Recognition","url":"/task/fine-grained-visual-recognition","datasets_with_task":"/datasets/task/fine-grained-visual-recognition"}],"languages":[],"variants":["Stanford Dogs","Stanford Dogs 5-way (1-shot)","Stanford Dogs 5-way (5-shot)"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/stanford_dogs","frameworks":["tf","jax"]}],"num_papers_in_archive":57,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/fine-grained-image-classification-on-stanford-1","task":"Fine-Grained Image Classification","dataset_variant":"Stanford Dogs","rows":24,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MP","paper":"/paper/sr-gnn-spatial-relation-aware-graph-neural","metrics":{"Accuracy":"97.3%"},"code_links":[{"title":"ardhendubehera/sr-gnn","url":"https://github.com/ardhendubehera/sr-gnn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-1","task":"Few-Shot Image Classification","dataset_variant":"Stanford Dogs 5-way (5-shot)","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MML(KL)","paper":"/paper/multi-level-metric-learning-for-few-shot","metrics":{"Accuracy":"75.59"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-clustering-on-stanford-dogs","task":"Image Clustering","dataset_variant":"Stanford Dogs","rows":4,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"FineGAN","paper":"/paper/finegan-unsupervised-hierarchical","metrics":{"Accuracy":"0.079","NMI":"0.233"},"code_links":[{"title":"kkanshul/finegan","url":"https://github.com/kkanshul/finegan"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-stanford-dogs","task":"Image Generation","dataset_variant":"Stanford Dogs","rows":4,"metrics":["FID","Inception score"],"first_row_in_archive_order":{"model":"Projected GAN","paper":"/paper/projected-gans-converge-faster","metrics":{"FID":"11.75"},"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/few-shot-image-classification-on-stanford","task":"Few-Shot Image Classification","dataset_variant":"Stanford Dogs 5-way (1-shot)","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MML(KL)","paper":"/paper/multi-level-metric-learning-for-few-shot","metrics":{"Accuracy":"59.05"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fine-grained-visual-recognition-on-stanford-2","task":"Fine-Grained Visual Recognition","dataset_variant":"Stanford Dogs","rows":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Selfsynthx","paper":"/paper/enhancing-cognition-and-explainability-of","metrics":{"Accuracy (%)":"86.91"},"code_links":[{"title":"sycny/selfsynthx","url":"https://github.com/sycny/selfsynthx"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/structural-feature-enhanced-transformer-for","title":"Structural feature enhanced transformer for fine-grained image recognition","date":"2025-06-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enhancing-cognition-and-explainability-of","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","date":"2025-02-19","rows_on_this_dataset":1,"code_links":1,"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/an-attention-locating-algorithm-for","title":"An Attention-Locating Algorithm for Eliminating Background Effects in Fine-grained Visual Classification","date":"2025-01-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sim-ofe-structure-information-mining-and","title":"SIM-OFE: Structure Information Mining and Object-aware Feature Enhancement for Fine-Grained Visual Categorization","date":"2024-09-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-granularity-part-sampling-attention-for","title":"Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification","date":"2024-08-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/delving-into-multimodal-prompting-for-fine","title":"Delving into Multimodal Prompting for Fine-grained Visual Classification","date":"2023-09-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/advisingnets-learning-to-distinguish-correct","title":"PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans","date":"2023-08-25","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/understanding-gaussian-attention-bias-of","title":"Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields","date":"2023-05-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/a-continual-development-methodology-for-large","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","date":"2022-09-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/vit-net-interpretable-vision-transformers","title":"ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder","date":"2022-07-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/on-the-eigenvalues-of-global-covariance","title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","date":"2022-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":3,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fine-grained-visual-classification-using-self","title":"Fine-Grained Visual Classification using Self Assessment Classifier","date":"2022-05-21","rows_on_this_dataset":1,"code_links":1,"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-free-lunch-from-vit-adaptive-attention","title":"A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition","date":"2021-10-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rams-trans-recurrent-attention-multi-scale","title":"RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition","date":"2021-07-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/transformer-with-peak-suppression-and","title":"Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition","date":"2021-07-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/feature-fusion-vision-transformer-fine","title":"Feature Fusion Vision Transformer for Fine-Grained Visual Categorization","date":"2021-07-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-level-metric-learning-for-few-shot","title":"Multi-level Metric Learning for Few-shot Image Recognition","date":"2021-03-21","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/transfg-a-transformer-architecture-for-fine","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","date":"2021-03-14","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":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-scale-adaptive-task-attention-network","title":"Multi-scale Adaptive Task Attention Network for Few-Shot Learning","date":"2020-11-30","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"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/learning-semantically-enhanced-feature-for","title":"Learning Semantically Enhanced Feature for Fine-Grained Image Classification","date":"2020-06-24","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/2003-13549","title":"Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets","date":"2020-03-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-attentive-pairwise-interaction-for","title":"Learning Attentive Pairwise Interaction for Fine-Grained Classification","date":"2020-02-24","rows_on_this_dataset":1,"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":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fine-grained-recognition-accounting-for","title":"Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes","date":"2019-12-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/revisiting-local-descriptor-based-image-to","title":"Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning","date":"2019-03-28","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/finegan-unsupervised-hierarchical","title":"FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery","date":"2018-11-27","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/few-shot-learning-with-graph-neural-networks","title":"Few-Shot Learning with Graph Neural Networks","date":"2017-11-10","rows_on_this_dataset":1,"code_links":6,"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/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/deep-clustering-via-joint-convolutional","title":"Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization","date":"2017-04-20","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/prototypical-networks-for-few-shot-learning","title":"Prototypical Networks for Few-shot Learning","date":"2017-03-15","rows_on_this_dataset":1,"code_links":43,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":64,"samples_ran":49,"samples_unverified":15,"pointer_only_for_licence":18,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lr-gan-layered-recursive-generative","title":"LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation","date":"2017-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/matching-networks-for-one-shot-learning","title":"Matching Networks for One Shot Learning","date":"2016-06-13","rows_on_this_dataset":1,"code_links":26,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":6,"samples_unverified":10,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/infogan-interpretable-representation-learning","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","date":"2016-06-12","rows_on_this_dataset":1,"code_links":38,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/joint-unsupervised-learning-of-deep","title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","date":"2016-04-13","rows_on_this_dataset":1,"code_links":3,"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."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":10,"samples_harvested":161,"samples_ran":108,"samples_unverified":53,"pointer_only_for_licence":36,"papers_with_no_sample_that_ran":1,"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."}