{"url":"/dataset/oxford-iiit-pets-1","name":"Oxford-IIIT Pets","full_name":null,"description_markdown":"The Oxford-IIIT Pet Dataset is a 37-category pet dataset with roughly 200 images for each class. The images have large variations in scale, pose, and lighting. All images have an associated ground truth annotation of breed, head ROI, and pixel-level trimap segmentation.","description_withheld":null,"homepage":"https://www.robots.ox.ac.uk/~vgg/data/pets/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-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":"Prompt Engineering","url":"/task/prompt-engineering","datasets_with_task":"/datasets/task/prompt-engineering"},{"name":"Image Compression","url":"/task/image-compression","datasets_with_task":"/datasets/task/image-compression"}],"languages":[],"variants":["Oxford-IIIT Pet Dataset","Oxford-IIIT Pets"],"data_loaders":[],"num_papers_in_archive":59,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/fine-grained-image-classification-on-oxford-2","task":"Fine-Grained Image Classification","dataset_variant":"Oxford-IIIT Pets","rows":19,"metrics":["Accuracy","Top-1 Error Rate","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"EffNet-L2 (SAM)","paper":"/paper/sharpness-aware-minimization-for-efficiently-1","metrics":{"Accuracy":"97.10","Top-1 Error Rate":"2.90%"},"code_links":[{"title":"davda54/sam","url":"https://github.com/davda54/sam"},{"title":"google-research/sam","url":"https://github.com/google-research/sam"},{"title":"moskomule/sam.pytorch","url":"https://github.com/moskomule/sam.pytorch"},{"title":"simon20010923/DDAMFN","url":"https://github.com/simon20010923/DDAMFN"},{"title":"ys-zong/medfair","url":"https://github.com/ys-zong/medfair"},{"title":"sayakpaul/Sharpness-Aware-Minimization-TensorFlow","url":"https://github.com/sayakpaul/Sharpness-Aware-Minimization-TensorFlow"},{"title":"wangermeng2021/Scaled-YOLOv4-tensorflow2","url":"https://github.com/wangermeng2021/Scaled-YOLOv4-tensorflow2"},{"title":"Jannoshh/simple-sam","url":"https://github.com/Jannoshh/simple-sam"},{"title":"rollovd/LookSAM","url":"https://github.com/rollovd/LookSAM"},{"title":"wangermeng2021/FastClassification","url":"https://github.com/wangermeng2021/FastClassification"},{"title":"borealisai/perturbed-forgetting","url":"https://github.com/borealisai/perturbed-forgetting"},{"title":"mhassann22/GCSAM","url":"https://github.com/mhassann22/GCSAM"},{"title":"Janus-Shiau/SAM-tf2","url":"https://github.com/Janus-Shiau/SAM-tf2"},{"title":"NiMlr/pynlqn","url":"https://github.com/NiMlr/pynlqn"},{"title":"Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation","url":"https://github.com/Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation"},{"title":"Yuheon/Sharp-Aware-Minimization","url":"https://github.com/Yuheon/Sharp-Aware-Minimization"},{"title":"denizyuret/playground","url":"https://github.com/denizyuret/playground"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/Scalable-Sharpness-Aware-Minimization"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-oxford-iiit-pets-1","task":"Image Classification","dataset_variant":"Oxford-IIIT Pets","rows":6,"metrics":["Accuracy","Per-Class Accuracy"],"first_row_in_archive_order":{"model":"CeiT-S (384 finetune resolution)","paper":"/paper/incorporating-convolution-designs-into-visual","metrics":{"Accuracy":"94.9"},"code_links":[{"title":"rishikksh20/CeiT-pytorch","url":"https://github.com/rishikksh20/CeiT-pytorch"},{"title":"coeusguo/ceit","url":"https://github.com/coeusguo/ceit"},{"title":"mindspore-courses/External-Attention-MindSpore","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/CeiT.py"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-learning-on-oxford-iiit-pets","task":"Zero-Shot Learning","dataset_variant":"Oxford-IIIT Pets","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZLaP","paper":"/paper/label-propagation-for-zero-shot","metrics":{"Accuracy":"90"},"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/image-clustering-on-oxford-iiit-pets","task":"Image Clustering","dataset_variant":"Oxford-IIIT Pets","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":"92.3"},"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-3","task":"Transductive Zero-Shot Classification","dataset_variant":"Oxford-IIIT Pets","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZLaP","paper":"/paper/label-propagation-for-zero-shot","metrics":{"Accuracy":"92.8"},"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/stochastic-subsampling-with-average-pooling","title":"Stochastic Subsampling With Average Pooling","date":"2024-09-25","rows_on_this_dataset":1,"code_links":0,"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/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/how-to-use-dropout-correctly-on-residual","title":"How to Use Dropout Correctly on Residual Networks with Batch Normalization","date":"2023-02-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/on-the-ideal-number-of-groups-for-isometric","title":"On the Ideal Number of Groups for Isometric Gradient Propagation","date":"2023-02-07","rows_on_this_dataset":1,"code_links":0,"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/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/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/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/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/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/neural-architecture-transfer","title":"Neural Architecture Transfer","date":"2020-05-12","rows_on_this_dataset":3,"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/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":2,"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."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":10,"samples_harvested":527,"samples_ran":337,"samples_unverified":190,"pointer_only_for_licence":170,"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."}