{"url":"/task/few-shot-image-classification","name":"Few-Shot Image Classification","slug":"few-shot-image-classification","description_markdown":"**Few-Shot Image Classification** is a computer vision task that involves training machine learning models to classify images into predefined categories using only a few labeled examples of each category (typically < 6 examples). The goal is to enable models to recognize and classify new images with minimal supervision and limited data, without having to train on large datasets. (typically < 6 examples)\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Learning Embedding Adaptation for Few-Shot Learning](https://github.com/Sha-Lab/FEAT) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":353,"papers_with_code":220,"benchmarks":89,"benchmark_tables_in_archive":89,"benchmark_tables_shown":89,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":24,"subtasks":3,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","slug":"few-shot-image-classification-on-mini-2","dataset":"Mini-Imagenet 5-way (1-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":105,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SgVA-CLIP","paper_title":"SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification","paper_url":"/paper/sgva-clip-semantic-guided-visual-adapting-of","paper_date":"2022-11-28","arxiv_id":"2211.16191","code_links":[{"title":"FannierPeng/SgVA-CLIP","url":"https://github.com/FannierPeng/SgVA-CLIP"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","slug":"few-shot-image-classification-on-mini-3","dataset":"Mini-Imagenet 5-way (5-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":95,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SgVA-CLIP","paper_title":"SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification","paper_url":"/paper/sgva-clip-semantic-guided-visual-adapting-of","paper_date":"2022-11-28","arxiv_id":"2211.16191","code_links":[{"title":"FannierPeng/SgVA-CLIP","url":"https://github.com/FannierPeng/SgVA-CLIP"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-1","slug":"few-shot-image-classification-on-tiered-1","dataset":"Tiered ImageNet 5-way (5-shot)","dataset_url":"/dataset/tieredimagenet","rows_in_archive":51,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CAML [Laion-2b]","paper_title":"Context-Aware Meta-Learning","paper_url":"/paper/context-aware-meta-learning","paper_date":"2023-10-17","arxiv_id":"2310.10971","code_links":[{"title":"cfifty/CAML","url":"https://github.com/cfifty/CAML"}],"syntology":{"n":16,"n_ran":5,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-tiered","slug":"few-shot-image-classification-on-tiered","dataset":"Tiered ImageNet 5-way (1-shot)","dataset_url":"/dataset/tieredimagenet","rows_in_archive":49,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CAML [Laion-2b]","paper_title":"Context-Aware Meta-Learning","paper_url":"/paper/context-aware-meta-learning","paper_date":"2023-10-17","arxiv_id":"2310.10971","code_links":[{"title":"cfifty/CAML","url":"https://github.com/cfifty/CAML"}],"syntology":{"n":16,"n_ran":5,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","slug":"few-shot-image-classification-on-cifar-fs-5-1","dataset":"CIFAR-FS 5-way (5-shot)","dataset_url":"/dataset/cifar-fs","rows_in_archive":39,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CAML [Laion-2b]","paper_title":"Context-Aware Meta-Learning","paper_url":"/paper/context-aware-meta-learning","paper_date":"2023-10-17","arxiv_id":"2310.10971","code_links":[{"title":"cfifty/CAML","url":"https://github.com/cfifty/CAML"}],"syntology":{"n":16,"n_ran":5,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","slug":"few-shot-image-classification-on-cifar-fs-5","dataset":"CIFAR-FS 5-way (1-shot)","dataset_url":"/dataset/cifar-fs","rows_in_archive":38,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PT+MAP+SF+SOT (transductive)","paper_title":"The Self-Optimal-Transport Feature Transform","paper_url":"/paper/the-self-optimal-transport-feature-transform","paper_date":"2022-04-06","arxiv_id":"2204.03065","code_links":[{"title":"danielshalam/bpa","url":"https://github.com/danielshalam/bpa"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","slug":"few-shot-image-classification-on-cub-200-5-1","dataset":"CUB 200 5-way 1-shot","dataset_url":"/dataset/cub-200-2011","rows_in_archive":36,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PT+MAP+SF+SOT (transductive)","paper_title":"The Self-Optimal-Transport Feature Transform","paper_url":"/paper/the-self-optimal-transport-feature-transform","paper_date":"2022-04-06","arxiv_id":"2204.03065","code_links":[{"title":"danielshalam/bpa","url":"https://github.com/danielshalam/bpa"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","slug":"few-shot-image-classification-on-cub-200-5","dataset":"CUB 200 5-way 5-shot","dataset_url":"/dataset/cub-200-2011","rows_in_archive":32,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CAML [Laion-2b]","paper_title":"Context-Aware Meta-Learning","paper_url":"/paper/context-aware-meta-learning","paper_date":"2023-10-17","arxiv_id":"2310.10971","code_links":[{"title":"cfifty/CAML","url":"https://github.com/cfifty/CAML"}],"syntology":{"n":16,"n_ran":5,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way","slug":"few-shot-image-classification-on-fc100-5-way","dataset":"FC100 5-way (1-shot)","dataset_url":"/dataset/fc100","rows_in_archive":22,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BAVARDAGE","paper_title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","paper_url":"/paper/adaptive-dimension-reduction-and-variational","paper_date":"2022-09-18","arxiv_id":"2209.08527","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-1","slug":"few-shot-image-classification-on-fc100-5-way-1","dataset":"FC100 5-way (5-shot)","dataset_url":"/dataset/fc100","rows_in_archive":22,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BAVARDAGE","paper_title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","paper_url":"/paper/adaptive-dimension-reduction-and-variational","paper_date":"2022-09-18","arxiv_id":"2209.08527","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-meta-dataset","slug":"few-shot-image-classification-on-meta-dataset","dataset":"Meta-Dataset","dataset_url":"/dataset/meta-dataset","rows_in_archive":22,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SMAT (DINO-VIT-Base-16-224)","paper_title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","paper_url":"/paper/unleashing-the-power-of-meta-tuning-for-few","paper_date":"2024-03-13","arxiv_id":"2403.08477","code_links":[{"title":"szc12153/sparse_meta_tuning","url":"https://github.com/szc12153/sparse_meta_tuning"}],"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-1","slug":"few-shot-image-classification-on-omniglot-1-1","dataset":"OMNIGLOT - 1-Shot, 20-way","dataset_url":null,"rows_in_archive":20,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GCR","paper_title":"Few-Shot Learning with Global Class Representations","paper_url":"/paper/few-shot-learning-with-global-class","paper_date":"2019-08-14","arxiv_id":"1908.05257","code_links":[{"title":"tiangeluo/fsl-global","url":"https://github.com/tiangeluo/fsl-global"},{"title":"huang-research-group/globalfsl2019","url":"https://github.com/huang-research-group/globalfsl2019"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-1","slug":"few-shot-image-classification-on-omniglot-5-1","dataset":"OMNIGLOT - 5-Shot, 20-way","dataset_url":null,"rows_in_archive":19,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MC2+","paper_title":"Meta-Curvature","paper_url":"/paper/meta-curvature","paper_date":"2019-02-09","arxiv_id":"1902.03356","code_links":[{"title":"silverbottlep/meta_curvature","url":"https://github.com/silverbottlep/meta_curvature"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-2","slug":"few-shot-image-classification-on-omniglot-1-2","dataset":"OMNIGLOT - 1-Shot, 5-way","dataset_url":null,"rows_in_archive":17,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MC2+","paper_title":"Meta-Curvature","paper_url":"/paper/meta-curvature","paper_date":"2019-02-09","arxiv_id":"1902.03356","code_links":[{"title":"silverbottlep/meta_curvature","url":"https://github.com/silverbottlep/meta_curvature"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-1","slug":"few-shot-image-classification-on-mini-1","dataset":"Mini-ImageNet - 1-Shot Learning","dataset_url":"/dataset/mini-imagenet","rows_in_archive":16,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PT+MAP","paper_title":"Leveraging the Feature Distribution in Transfer-based Few-Shot Learning","paper_url":"/paper/leveraging-the-feature-distribution-in","paper_date":"2020-06-06","arxiv_id":"2006.03806","code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"yhu01/PT-MAP","url":"https://github.com/yhu01/PT-MAP"},{"title":"yhu01/bms","url":"https://github.com/yhu01/bms"},{"title":"xiangyu8/PT-MAP-sf","url":"https://github.com/xiangyu8/PT-MAP-sf"},{"title":"allenhaozhu/ease","url":"https://github.com/allenhaozhu/ease"},{"title":"mbonto/fewshot_neuroimaging_classification","url":"https://github.com/mbonto/fewshot_neuroimaging_classification"}],"syntology":{"n":26,"n_ran":10,"n_unverified":16,"n_pointer_only":11}}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-2","slug":"few-shot-image-classification-on-omniglot-5-2","dataset":"OMNIGLOT - 5-Shot, 5-way","dataset_url":null,"rows_in_archive":16,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DCN6-E","paper_title":"Decoder Choice Network for Meta-Learning","paper_url":"/paper/decoder-choice-network-for-meta-learning","paper_date":"2019-09-25","arxiv_id":"1909.11446","code_links":[{"title":"AceChuse/DCN","url":"https://github.com/AceChuse/DCN"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-12","slug":"few-shot-image-classification-on-mini-12","dataset":"Mini-Imagenet 10-way (1-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":14,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Transductive CNAPS + FETI","paper_title":"Enhancing Few-Shot Image Classification with Unlabelled Examples","paper_url":"/paper/improving-few-shot-visual-classification-with","paper_date":"2020-06-17","arxiv_id":"2006.12245","code_links":[{"title":"peymanbateni/simple-cnaps","url":"https://github.com/peymanbateni/simple-cnaps"},{"title":"plai-group/simple-cnaps","url":"https://github.com/plai-group/simple-cnaps"}],"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-13","slug":"few-shot-image-classification-on-mini-13","dataset":"Mini-Imagenet 10-way (5-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":14,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Transductive CNAPS + FETI","paper_title":"Enhancing Few-Shot Image Classification with Unlabelled Examples","paper_url":"/paper/improving-few-shot-visual-classification-with","paper_date":"2020-06-17","arxiv_id":"2006.12245","code_links":[{"title":"peymanbateni/simple-cnaps","url":"https://github.com/peymanbateni/simple-cnaps"},{"title":"plai-group/simple-cnaps","url":"https://github.com/plai-group/simple-cnaps"}],"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-meta-dataset-1","slug":"few-shot-image-classification-on-meta-dataset-1","dataset":"Meta-Dataset Rank","dataset_url":"/dataset/meta-dataset","rows_in_archive":13,"metrics":["Mean Rank"],"first_row_in_archive_order":{"model":"URT","paper_title":"A Universal Representation Transformer Layer for Few-Shot Image Classification","paper_url":"/paper/a-universal-representation-transformer-layer","paper_date":"2020-06-21","arxiv_id":"2006.11702","code_links":[{"title":"liulu112601/URT","url":"https://github.com/liulu112601/URT"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-2","slug":"few-shot-image-classification-on-tiered-2","dataset":"Tiered ImageNet 10-way (1-shot)","dataset_url":"/dataset/tieredimagenet","rows_in_archive":13,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Transductive CNAPS + FETI","paper_title":"Enhancing Few-Shot Image Classification with Unlabelled Examples","paper_url":"/paper/improving-few-shot-visual-classification-with","paper_date":"2020-06-17","arxiv_id":"2006.12245","code_links":[{"title":"peymanbateni/simple-cnaps","url":"https://github.com/peymanbateni/simple-cnaps"},{"title":"plai-group/simple-cnaps","url":"https://github.com/plai-group/simple-cnaps"}],"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-3","slug":"few-shot-image-classification-on-tiered-3","dataset":"Tiered ImageNet 10-way (5-shot)","dataset_url":"/dataset/tieredimagenet","rows_in_archive":13,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Transductive CNAPS + FETI","paper_title":"Enhancing Few-Shot Image Classification with Unlabelled Examples","paper_url":"/paper/improving-few-shot-visual-classification-with","paper_date":"2020-06-17","arxiv_id":"2006.12245","code_links":[{"title":"peymanbateni/simple-cnaps","url":"https://github.com/peymanbateni/simple-cnaps"},{"title":"plai-group/simple-cnaps","url":"https://github.com/plai-group/simple-cnaps"}],"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet","slug":"few-shot-image-classification-on-dirichlet","dataset":"Dirichlet Mini-Imagenet (5-way, 1-shot)","dataset_url":null,"rows_in_archive":12,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"BAVARDAGE","paper_title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","paper_url":"/paper/adaptive-dimension-reduction-and-variational","paper_date":"2022-09-18","arxiv_id":"2209.08527","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-1","slug":"few-shot-image-classification-on-dirichlet-1","dataset":"Dirichlet Mini-Imagenet (5-way, 5-shot)","dataset_url":null,"rows_in_archive":12,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"BAVARDAGE","paper_title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","paper_url":"/paper/adaptive-dimension-reduction-and-variational","paper_date":"2022-09-18","arxiv_id":"2209.08527","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-5","slug":"few-shot-image-classification-on-mini-5","dataset":"Mini-ImageNet-CUB 5-way (1-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":12,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TRIDENT","paper_title":"Transductive Decoupled Variational Inference for Few-Shot Classification","paper_url":"/paper/transductive-decoupled-variational-inference","paper_date":"2022-08-22","arxiv_id":"2208.10559","code_links":[{"title":"anujinho/trident","url":"https://github.com/anujinho/trident"}],"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-bongard-hoi","slug":"few-shot-image-classification-on-bongard-hoi","dataset":"Bongard-HOI","dataset_url":"/dataset/bongard-hoi","rows_in_archive":9,"metrics":["Avg. Accuracy"],"first_row_in_archive_order":{"model":"Human (Amateur)","paper_title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","paper_url":"/paper/bongard-hoi-benchmarking-few-shot-visual","paper_date":"2022-05-27","arxiv_id":"2205.13803","code_links":[{"title":"nvlabs/bongard-hoi","url":"https://github.com/nvlabs/bongard-hoi"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-2","slug":"few-shot-image-classification-on-dirichlet-2","dataset":"Dirichlet Tiered-Imagenet (5-way, 1-shot)","dataset_url":null,"rows_in_archive":9,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"BAVARDAGE","paper_title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","paper_url":"/paper/adaptive-dimension-reduction-and-variational","paper_date":"2022-09-18","arxiv_id":"2209.08527","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-3","slug":"few-shot-image-classification-on-dirichlet-3","dataset":"Dirichlet Tiered-Imagenet (5-way, 5-shot)","dataset_url":null,"rows_in_archive":9,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"\\alpha-TIM","paper_title":"Realistic Evaluation of Transductive Few-Shot Learning","paper_url":"/paper/realistic-evaluation-of-transductive-few-shot-1","paper_date":"2022-04-24","arxiv_id":"2204.11181","code_links":[{"title":"oveilleux/realistic_transductive_few_shot","url":"https://github.com/oveilleux/realistic_transductive_few_shot"}],"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":10}}},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-4","slug":"few-shot-image-classification-on-dirichlet-4","dataset":"Dirichlet CUB-200 (5-way, 1-shot)","dataset_url":null,"rows_in_archive":8,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"BAVARDAGE","paper_title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","paper_url":"/paper/adaptive-dimension-reduction-and-variational","paper_date":"2022-09-18","arxiv_id":"2209.08527","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-5","slug":"few-shot-image-classification-on-dirichlet-5","dataset":"Dirichlet CUB-200 (5-way, 5-shot)","dataset_url":null,"rows_in_archive":8,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"BAVARDAGE","paper_title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","paper_url":"/paper/adaptive-dimension-reduction-and-variational","paper_date":"2022-09-18","arxiv_id":"2209.08527","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-1-1","slug":"few-shot-image-classification-on-imagenet-1-1","dataset":"ImageNet - 1-shot","dataset_url":"/dataset/imagenet","rows_in_archive":8,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"ViT-MoE-15B (Every-2)","paper_title":"Scaling Vision with Sparse Mixture of Experts","paper_url":"/paper/scaling-vision-with-sparse-mixture-of-experts","paper_date":"2021-06-10","arxiv_id":"2106.05974","code_links":[{"title":"google-research/vmoe","url":"https://github.com/google-research/vmoe"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-5","slug":"few-shot-image-classification-on-imagenet-5","dataset":"ImageNet - 5-shot","dataset_url":"/dataset/imagenet","rows_in_archive":8,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"ViT-MoE-15B (Every-2)","paper_title":"Scaling Vision with Sparse Mixture of Experts","paper_url":"/paper/scaling-vision-with-sparse-mixture-of-experts","paper_date":"2021-06-10","arxiv_id":"2106.05974","code_links":[{"title":"google-research/vmoe","url":"https://github.com/google-research/vmoe"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-1","slug":"few-shot-image-classification-on-imagenet-fs-1","dataset":"ImageNet-FS (2-shot, novel)","dataset_url":null,"rows_in_archive":8,"metrics":["Top-5 Accuracy (%)"],"first_row_in_archive_order":{"model":"KGTN-ens (ResNet-50, h+g, max)","paper_title":"KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles","paper_url":"/paper/kgtn-ens-few-shot-image-classification-with","paper_date":"2022-11-06","arxiv_id":"2211.03199","code_links":[{"title":"DominikFilipiak/KGTN-ens","url":"https://github.com/DominikFilipiak/KGTN-ens"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-6","slug":"few-shot-image-classification-on-imagenet-fs-6","dataset":"ImageNet-FS (5-shot, all)","dataset_url":null,"rows_in_archive":8,"metrics":["Top-5 Accuracy (%)"],"first_row_in_archive_order":{"model":"KGTN-ens (ResNet-50, h+g, max)","paper_title":"KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles","paper_url":"/paper/kgtn-ens-few-shot-image-classification-with","paper_date":"2022-11-06","arxiv_id":"2211.03199","code_links":[{"title":"DominikFilipiak/KGTN-ens","url":"https://github.com/DominikFilipiak/KGTN-ens"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-6","slug":"few-shot-image-classification-on-mini-6","dataset":"Mini-ImageNet-CUB 5-way (5-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TRIDENT","paper_title":"Transductive Decoupled Variational Inference for Few-Shot Classification","paper_url":"/paper/transductive-decoupled-variational-inference","paper_date":"2022-08-22","arxiv_id":"2208.10559","code_links":[{"title":"anujinho/trident","url":"https://github.com/anujinho/trident"}],"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-10","slug":"few-shot-image-classification-on-imagenet-10","dataset":"ImageNet - 10-shot","dataset_url":"/dataset/imagenet","rows_in_archive":7,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MAWS (ViT-6.5B)","paper_title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","paper_url":"/paper/the-effectiveness-of-mae-pre-pretraining-for","paper_date":"2023-03-23","arxiv_id":"2303.13496","code_links":[{"title":"facebookresearch/maws","url":"https://github.com/facebookresearch/maws"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs","slug":"few-shot-image-classification-on-imagenet-fs","dataset":"ImageNet-FS (1-shot, novel)","dataset_url":null,"rows_in_archive":7,"metrics":["Top-5 Accuracy (%)"],"first_row_in_archive_order":{"model":"KGTN-ens (ResNet-50, h+g, max)","paper_title":"KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles","paper_url":"/paper/kgtn-ens-few-shot-image-classification-with","paper_date":"2022-11-06","arxiv_id":"2211.03199","code_links":[{"title":"DominikFilipiak/KGTN-ens","url":"https://github.com/DominikFilipiak/KGTN-ens"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-7","slug":"few-shot-image-classification-on-mini-7","dataset":"Mini-Imagenet 20-way (1-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TIM-GD","paper_title":"Transductive Information Maximization For Few-Shot Learning","paper_url":"/paper/transductive-information-maximization-for-few","paper_date":"2020-08-25","arxiv_id":"2008.11297","code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"mboudiaf/TIM","url":"https://github.com/mboudiaf/TIM"}],"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-8","slug":"few-shot-image-classification-on-mini-8","dataset":"Mini-Imagenet 20-way (5-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TIM-GD","paper_title":"Transductive Information Maximization For Few-Shot Learning","paper_url":"/paper/transductive-information-maximization-for-few","paper_date":"2020-08-25","arxiv_id":"2008.11297","code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"mboudiaf/TIM","url":"https://github.com/mboudiaf/TIM"}],"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-1","slug":"few-shot-image-classification-on-stanford-1","dataset":"Stanford Dogs 5-way (5-shot)","dataset_url":"/dataset/stanford-dogs","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MML(KL)","paper_title":"Multi-level Metric Learning for Few-shot Image Recognition","paper_url":"/paper/multi-level-metric-learning-for-few-shot","paper_date":"2021-03-21","arxiv_id":"2103.11383","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-2","slug":"few-shot-image-classification-on-stanford-2","dataset":"Stanford Cars 5-way (1-shot)","dataset_url":"/dataset/stanford-cars","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MATANet","paper_title":"Multi-scale Adaptive Task Attention Network for Few-Shot Learning","paper_url":"/paper/multi-scale-adaptive-task-attention-network","paper_date":"2020-11-30","arxiv_id":"2011.14479","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-3","slug":"few-shot-image-classification-on-stanford-3","dataset":"Stanford Cars 5-way (5-shot)","dataset_url":"/dataset/stanford-cars","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MATANet","paper_title":"Multi-scale Adaptive Task Attention Network for Few-Shot Learning","paper_url":"/paper/multi-scale-adaptive-task-attention-network","paper_date":"2020-11-30","arxiv_id":"2011.14479","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-2011-1","slug":"few-shot-image-classification-on-cub-200-2011-1","dataset":"CUB-200-2011 - 0-Shot","dataset_url":"/dataset/cub-200-2011","rows_in_archive":5,"metrics":["Top-1 Accuracy","AP50"],"first_row_in_archive_order":{"model":"Word CNN-RNN (DS-SJE Embedding)","paper_title":"Learning Deep Representations of Fine-grained Visual Descriptions","paper_url":"/paper/learning-deep-representations-of-fine-grained","paper_date":"2016-05-17","arxiv_id":"1605.05395","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"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-0","slug":"few-shot-image-classification-on-imagenet-0","dataset":"ImageNet - 0-Shot","dataset_url":"/dataset/imagenet","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DebiasPL (ResNet50)","paper_title":"Debiased Learning from Naturally Imbalanced Pseudo-Labels","paper_url":"/paper/debiased-learning-from-naturally-imbalanced","paper_date":"2022-01-05","arxiv_id":"2201.01490","code_links":[{"title":"frank-xwang/debiased-pseudo-labeling","url":"https://github.com/frank-xwang/debiased-pseudo-labeling"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-4","slug":"few-shot-image-classification-on-mini-4","dataset":"Mini-Imagenet 5-way (10-shot)","dataset_url":"/dataset/mini-imagenet","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PT+MAP","paper_title":"Leveraging the Feature Distribution in Transfer-based Few-Shot Learning","paper_url":"/paper/leveraging-the-feature-distribution-in","paper_date":"2020-06-06","arxiv_id":"2006.03806","code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"yhu01/PT-MAP","url":"https://github.com/yhu01/PT-MAP"},{"title":"yhu01/bms","url":"https://github.com/yhu01/bms"},{"title":"xiangyu8/PT-MAP-sf","url":"https://github.com/xiangyu8/PT-MAP-sf"},{"title":"allenhaozhu/ease","url":"https://github.com/allenhaozhu/ease"},{"title":"mbonto/fewshot_neuroimaging_classification","url":"https://github.com/mbonto/fewshot_neuroimaging_classification"}],"syntology":{"n":26,"n_ran":10,"n_unverified":16,"n_pointer_only":11}}},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-50","slug":"few-shot-image-classification-on-cub-200-50","dataset":"CUB 200 50-way (0-shot)","dataset_url":"/dataset/cub-200-2011","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Prototypical Networks","paper_title":"Prototypical Networks for Few-shot Learning","paper_url":"/paper/prototypical-networks-for-few-shot-learning","paper_date":"2017-03-15","arxiv_id":"1703.05175","code_links":[{"title":"learnables/learn2learn","url":"https://github.com/learnables/learn2learn"},{"title":"oscarknagg/few-shot","url":"https://github.com/oscarknagg/few-shot"},{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"jakesnell/prototypical-networks","url":"https://github.com/jakesnell/prototypical-networks"},{"title":"orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch","url":"https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch"},{"title":"Sha-Lab/FEAT","url":"https://github.com/Sha-Lab/FEAT"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/ProtoNet"},{"title":"cyvius96/prototypical-network-pytorch","url":"https://github.com/cyvius96/prototypical-network-pytorch"},{"title":"Hsankesara/DeepResearch","url":"https://github.com/Hsankesara/DeepResearch"},{"title":"cnguyen10/few_shot_meta_learning","url":"https://github.com/cnguyen10/few_shot_meta_learning"},{"title":"cnielly/prototypical-networks-omniglot","url":"https://github.com/cnielly/prototypical-networks-omniglot"},{"title":"schatty/prototypical-networks-tf","url":"https://github.com/schatty/prototypical-networks-tf"},{"title":"goldblum/AdversarialQuerying","url":"https://github.com/goldblum/AdversarialQuerying"},{"title":"amazon-research/dse","url":"https://github.com/amazon-research/dse"},{"title":"hrdwsong/ProtoNet-Paddle","url":"https://github.com/hrdwsong/ProtoNet-Paddle"},{"title":"ebadrian/metadl","url":"https://github.com/ebadrian/metadl"},{"title":"maxstrobel/HCN-PrototypeLoss-PyTorch","url":"https://github.com/maxstrobel/HCN-PrototypeLoss-PyTorch"},{"title":"barnrang/Prototypical-network-keras-reimplementation","url":"https://github.com/barnrang/Prototypical-network-keras-reimplementation"},{"title":"fabian57fabian/prototypical-networks-few-shot-learning","url":"https://github.com/fabian57fabian/prototypical-networks-few-shot-learning"},{"title":"RongKaiWeskerMA/INSTA","url":"https://github.com/RongKaiWeskerMA/INSTA"},{"title":"jsalbert/prototypical-networks","url":"https://github.com/jsalbert/prototypical-networks"},{"title":"ajfisch/few-shot-cp","url":"https://github.com/ajfisch/few-shot-cp"},{"title":"msfuxian/DualAttentionNet","url":"https://github.com/msfuxian/DualAttentionNet"},{"title":"DrMMZ/ProtoNet","url":"https://github.com/DrMMZ/ProtoNet"},{"title":"skingorz/prototypeNet-paddle","url":"https://github.com/skingorz/prototypeNet-paddle"},{"title":"ulises-jeremias/prototypical-networks-tf","url":"https://github.com/ulises-jeremias/prototypical-networks-tf"},{"title":"KamalM8/Few-Shot-learning-Fashion","url":"https://github.com/KamalM8/Few-Shot-learning-Fashion"},{"title":"Michedev/Prototypical-Networks","url":"https://github.com/Michedev/Prototypical-Networks"},{"title":"joshfp/one-shot-learning","url":"https://github.com/joshfp/one-shot-learning"},{"title":"andrewbo29/mtm-meta-learning-sa","url":"https://github.com/andrewbo29/mtm-meta-learning-sa"},{"title":"joshfp/fellowship.ai","url":"https://github.com/joshfp/fellowship.ai"},{"title":"mariehane/prototypical-networks","url":"https://github.com/mariehane/prototypical-networks"},{"title":"WangTianduo/Prototypical-Networks","url":"https://github.com/WangTianduo/Prototypical-Networks"},{"title":"ash3n/Prototypical-Network-TF","url":"https://github.com/ash3n/Prototypical-Network-TF"},{"title":"ash3n/Latent-Similarity","url":"https://github.com/ash3n/Latent-Similarity"},{"title":"minseop-aitrics/FewshotLearning","url":"https://github.com/minseop-aitrics/FewshotLearning"},{"title":"akshatgarg99/FewShotLearning","url":"https://github.com/akshatgarg99/FewShotLearning"},{"title":"yangcedrus/ProtoNet","url":"https://github.com/yangcedrus/ProtoNet"},{"title":"HenryCWoo/LTLProject","url":"https://github.com/HenryCWoo/LTLProject"},{"title":"lif31up/prototypical-network","url":"https://github.com/lif31up/prototypical-network"},{"title":"yredwood/fewshot_blogpost","url":"https://github.com/yredwood/fewshot_blogpost"},{"title":"zz990704/Reimplementation-Prototypical-network","url":"https://github.com/zz990704/Reimplementation-Prototypical-network"},{"title":"COAOX/Cifar-Prototypical","url":"https://github.com/COAOX/Cifar-Prototypical"}],"syntology":{"n":64,"n_ran":49,"n_unverified":15,"n_pointer_only":18}}},{"leaderboard":"/sota/few-shot-image-classification-on-caltech-256","slug":"few-shot-image-classification-on-caltech-256","dataset":"Caltech-256 5-way (1-shot)","dataset_url":"/dataset/caltech-256","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"UL-Hopfield (ULH)","paper_title":"Unsupervised Learning using Pretrained CNN and Associative Memory Bank","paper_url":"/paper/unsupervised-learning-using-pretrained-cnn","paper_date":"2018-05-02","arxiv_id":"1805.01033","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-0","slug":"few-shot-image-classification-on-cub-200-0","dataset":"CUB-200 - 0-Shot Learning","dataset_url":"/dataset/cub-200-2011","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TAFE-Net","paper_title":"TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning","paper_url":"/paper/tafe-net-task-aware-feature-embeddings-for-1","paper_date":"2019-04-11","arxiv_id":"1904.05967","code_links":[{"title":"ucbdrive/tafe-net","url":"https://github.com/ucbdrive/tafe-net"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-2","slug":"few-shot-image-classification-on-imagenet-fs-2","dataset":"ImageNet-FS (5-shot, novel)","dataset_url":null,"rows_in_archive":3,"metrics":["Top-5 Accuracy (%)"],"first_row_in_archive_order":{"model":"KGTN-ens (ResNet-50, h+g, mean)","paper_title":"KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles","paper_url":"/paper/kgtn-ens-few-shot-image-classification-with","paper_date":"2022-11-06","arxiv_id":"2211.03199","code_links":[{"title":"DominikFilipiak/KGTN-ens","url":"https://github.com/DominikFilipiak/KGTN-ens"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-orbit","slug":"few-shot-image-classification-on-orbit","dataset":"ORBIT Clutter Video Evaluation","dataset_url":"/dataset/orbit","rows_in_archive":3,"metrics":["Frame accuracy"],"first_row_in_archive_order":{"model":"ProtoNetsVideo","paper_title":"Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022","paper_url":"/paper/improving-protonet-for-few-shot-video-object","paper_date":"2022-10-01","arxiv_id":"2210.00174","code_links":[{"title":"guliisgreat/orbit-2022-winner-method","url":"https://github.com/guliisgreat/orbit-2022-winner-method"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/ProtoNet"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ProtoNet"},{"title":"2023-MindSpore-1/ms-code-215","url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/ProtoNet"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-stanford","slug":"few-shot-image-classification-on-stanford","dataset":"Stanford Dogs 5-way (1-shot)","dataset_url":"/dataset/stanford-dogs","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MML(KL)","paper_title":"Multi-level Metric Learning for Few-shot Image Recognition","paper_url":"/paper/multi-level-metric-learning-for-few-shot","paper_date":"2021-03-21","arxiv_id":"2103.11383","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cifar100-5","slug":"few-shot-image-classification-on-cifar100-5","dataset":"CIFAR100 5-way (1-shot)","dataset_url":"/dataset/cifar-100","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"UL-Hopfield (ULH)","paper_title":"Unsupervised Learning using Pretrained CNN and Associative Memory Bank","paper_url":"/paper/unsupervised-learning-using-pretrained-cnn","paper_date":"2018-05-02","arxiv_id":"1805.01033","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-1","slug":"few-shot-image-classification-on-imagenet-1","dataset":"ImageNet (1-shot)","dataset_url":null,"rows_in_archive":2,"metrics":["Top-5 Accuracy"],"first_row_in_archive_order":{"model":"TRAML","paper_title":"Boosting Few-Shot Learning With Adaptive Margin Loss","paper_url":"/paper/boosting-few-shot-learning-with-adaptive","paper_date":"2020-05-28","arxiv_id":"2005.13826","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-3","slug":"few-shot-image-classification-on-imagenet-fs-3","dataset":"ImageNet-FS (10-shot, novel)","dataset_url":null,"rows_in_archive":2,"metrics":["Top-5 Accuracy (%)"],"first_row_in_archive_order":{"model":"KGTN-ens (ResNet-50, h+g, max)","paper_title":"KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles","paper_url":"/paper/kgtn-ens-few-shot-image-classification-with","paper_date":"2022-11-06","arxiv_id":"2211.03199","code_links":[{"title":"DominikFilipiak/KGTN-ens","url":"https://github.com/DominikFilipiak/KGTN-ens"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-4","slug":"few-shot-image-classification-on-imagenet-fs-4","dataset":"ImageNet-FS (1-shot, all)","dataset_url":null,"rows_in_archive":2,"metrics":["Top-5 Accuracy (%)"],"first_row_in_archive_order":{"model":"KGTN-ens (ResNet-50, h+g, max)","paper_title":"KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles","paper_url":"/paper/kgtn-ens-few-shot-image-classification-with","paper_date":"2022-11-06","arxiv_id":"2211.03199","code_links":[{"title":"DominikFilipiak/KGTN-ens","url":"https://github.com/DominikFilipiak/KGTN-ens"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-5","slug":"few-shot-image-classification-on-imagenet-fs-5","dataset":"ImageNet-FS (2-shot, all)","dataset_url":null,"rows_in_archive":2,"metrics":["Top-5 Accuracy (%)"],"first_row_in_archive_order":{"model":"KGTN-ens (ResNet-50, h+g, max)","paper_title":"KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles","paper_url":"/paper/kgtn-ens-few-shot-image-classification-with","paper_date":"2022-11-06","arxiv_id":"2211.03199","code_links":[{"title":"DominikFilipiak/KGTN-ens","url":"https://github.com/DominikFilipiak/KGTN-ens"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-7","slug":"few-shot-image-classification-on-imagenet-fs-7","dataset":"ImageNet-FS (10-shot, all)","dataset_url":null,"rows_in_archive":2,"metrics":["Top-5 Accuracy (%)"],"first_row_in_archive_order":{"model":"KGTN (ResNet-50)","paper_title":"Knowledge Graph Transfer Network for Few-Shot Recognition","paper_url":"/paper/knowledge-graph-transfer-network-for-few-shot","paper_date":"2019-11-21","arxiv_id":"1911.09579","code_links":[{"title":"MyChocer/KGTN","url":"https://github.com/MyChocer/KGTN"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-10","slug":"few-shot-image-classification-on-mini-10","dataset":"Mini-ImageNet to CUB - 5 shot learning","dataset_url":"/dataset/mini-imagenet","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TIM-GD","paper_title":"Transductive Information Maximization For Few-Shot Learning","paper_url":"/paper/transductive-information-maximization-for-few","paper_date":"2020-08-25","arxiv_id":"2008.11297","code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"mboudiaf/TIM","url":"https://github.com/mboudiaf/TIM"}],"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot","slug":"few-shot-image-classification-on-omniglot","dataset":"OMNIGLOT-EMNIST 5-way (1-shot)","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"HyperShot","paper_title":"HyperShot: Few-Shot Learning by Kernel HyperNetworks","paper_url":"/paper/hypershot-few-shot-learning-by-kernel","paper_date":"2022-03-21","arxiv_id":"2203.11378","code_links":[{"title":"gmum/few-shot-hypernets-public","url":"https://github.com/gmum/few-shot-hypernets-public"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-2","slug":"few-shot-image-classification-on-omniglot-2","dataset":"OMNIGLOT-EMNIST 5-way (5-shot)","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"HyperShot","paper_title":"HyperShot: Few-Shot Learning by Kernel HyperNetworks","paper_url":"/paper/hypershot-few-shot-learning-by-kernel","paper_date":"2022-03-21","arxiv_id":"2203.11378","code_links":[{"title":"gmum/few-shot-hypernets-public","url":"https://github.com/gmum/few-shot-hypernets-public"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-orbit-clean","slug":"few-shot-image-classification-on-orbit-clean","dataset":"ORBIT Clean Video Evaluation","dataset_url":"/dataset/orbit","rows_in_archive":2,"metrics":["Frame accuracy"],"first_row_in_archive_order":{"model":"SimpleCNAPs + LITE","paper_title":"Memory Efficient Meta-Learning with Large Images","paper_url":"/paper/memory-efficient-meta-learning-with-large","paper_date":"2021-07-02","arxiv_id":"2107.01105","code_links":[{"title":"microsoft/ORBIT-Dataset","url":"https://github.com/microsoft/ORBIT-Dataset"},{"title":"cambridge-mlg/LITE","url":"https://github.com/cambridge-mlg/LITE"}],"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-sun-0-shot","slug":"few-shot-image-classification-on-sun-0-shot","dataset":"SUN - 0-Shot","dataset_url":"/dataset/sun","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Synthesised Classifier","paper_title":"Synthesized Classifiers for Zero-Shot Learning","paper_url":"/paper/synthesized-classifiers-for-zero-shot","paper_date":"2016-03-02","arxiv_id":"1603.00550","code_links":[{"title":"JudyYe/zero-shot-gcn","url":"https://github.com/JudyYe/zero-shot-gcn"},{"title":"ruotianluo/zsl-gcn-pth","url":"https://github.com/ruotianluo/zsl-gcn-pth"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":2}}},{"leaderboard":"/sota/few-shot-image-classification-on-apy-0-shot","slug":"few-shot-image-classification-on-apy-0-shot","dataset":"aPY - 0-Shot","dataset_url":"/dataset/apy","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TAFE-Net","paper_title":"TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning","paper_url":"/paper/tafe-net-task-aware-feature-embeddings-for-1","paper_date":"2019-04-11","arxiv_id":"1904.05967","code_links":[{"title":"ucbdrive/tafe-net","url":"https://github.com/ucbdrive/tafe-net"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-awa-0-shot","slug":"few-shot-image-classification-on-awa-0-shot","dataset":"AWA - 0-Shot","dataset_url":"/dataset/awa-1","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Synthesised Classifier","paper_title":"Synthesized Classifiers for Zero-Shot Learning","paper_url":"/paper/synthesized-classifiers-for-zero-shot","paper_date":"2016-03-02","arxiv_id":"1603.00550","code_links":[{"title":"JudyYe/zero-shot-gcn","url":"https://github.com/JudyYe/zero-shot-gcn"},{"title":"ruotianluo/zsl-gcn-pth","url":"https://github.com/ruotianluo/zsl-gcn-pth"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":2}}},{"leaderboard":"/sota/few-shot-image-classification-on-awa1-0-shot","slug":"few-shot-image-classification-on-awa1-0-shot","dataset":"AWA1 - 0-Shot","dataset_url":"/dataset/awa-1","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TAFE-Net","paper_title":"TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning","paper_url":"/paper/tafe-net-task-aware-feature-embeddings-for-1","paper_date":"2019-04-11","arxiv_id":"1904.05967","code_links":[{"title":"ucbdrive/tafe-net","url":"https://github.com/ucbdrive/tafe-net"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-awa2-0-shot","slug":"few-shot-image-classification-on-awa2-0-shot","dataset":"AWA2 - 0-Shot","dataset_url":"/dataset/awa2-1","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TAFE-Net","paper_title":"TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning","paper_url":"/paper/tafe-net-task-aware-feature-embeddings-for-1","paper_date":"2019-04-11","arxiv_id":"1904.05967","code_links":[{"title":"ucbdrive/tafe-net","url":"https://github.com/ucbdrive/tafe-net"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-image-classification-on-caltech-256-1","slug":"few-shot-image-classification-on-caltech-256-1","dataset":"Caltech-256 5-way (5-shot)","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MergedNet-Concat","paper_title":"MergedNET: A simple approach for one-shot learning in siamese networks based on similarity layers","paper_url":"/paper/mergednet-a-simple-approach-for-one-shot","paper_date":"2022-10-14","arxiv_id":null,"code_links":[{"title":"Amotica/MergedNET","url":"https://github.com/Amotica/MergedNET"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-caltech101","slug":"few-shot-image-classification-on-caltech101","dataset":"Caltech101","dataset_url":null,"rows_in_archive":1,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PRE","paper_title":"PRE: Vision-Language Prompt Learning with Reparameterization Encoder","paper_url":"/paper/pre-vision-language-prompt-learning-with","paper_date":"2023-09-14","arxiv_id":"2309.07760","code_links":[{"title":"minhanh151/pre","url":"https://github.com/minhanh151/pre"},{"title":"minhanh151/respro","url":"https://github.com/minhanh151/respro"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-1","slug":"few-shot-image-classification-on-cifar-fs-1","dataset":"CIFAR-FS - 1-Shot Learning","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"pseudo-shots","paper_title":"Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks","paper_url":"/paper/pseudo-shots-few-shot-learning-with-auxiliary","paper_date":"2020-12-13","arxiv_id":"2012.07176","code_links":[{"title":"BatsResearch/efsl","url":"https://github.com/BatsResearch/efsl"},{"title":"Reza-esfandiarpoor/pseudo-shots","url":"https://github.com/Reza-esfandiarpoor/pseudo-shots"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-2","slug":"few-shot-image-classification-on-cifar-fs-5-2","dataset":"CIFAR-FS - 5-Shot Learning","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"pseudo-shots","paper_title":"Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks","paper_url":"/paper/pseudo-shots-few-shot-learning-with-auxiliary","paper_date":"2020-12-13","arxiv_id":"2012.07176","code_links":[{"title":"BatsResearch/efsl","url":"https://github.com/BatsResearch/efsl"},{"title":"Reza-esfandiarpoor/pseudo-shots","url":"https://github.com/Reza-esfandiarpoor/pseudo-shots"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-2011","slug":"few-shot-image-classification-on-cub-200-2011","dataset":"CUB-200-2011 5-way (1-shot)","dataset_url":"/dataset/cub-200-2011","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MATANet","paper_title":"Multi-scale Adaptive Task Attention Network for Few-Shot Learning","paper_url":"/paper/multi-scale-adaptive-task-attention-network","paper_date":"2020-11-30","arxiv_id":"2011.14479","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-2011-2","slug":"few-shot-image-classification-on-cub-200-2011-2","dataset":"CUB-200-2011 5-way (5-shot)","dataset_url":"/dataset/cub-200-2011","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MATANet","paper_title":"Multi-scale Adaptive Task Attention Network for Few-Shot Learning","paper_url":"/paper/multi-scale-adaptive-task-attention-network","paper_date":"2020-11-30","arxiv_id":"2011.14479","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-2","slug":"few-shot-image-classification-on-cub-200-5-2","dataset":"CUB 200 5-way","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"EASY 3xResNet12 (transductive)","paper_title":"EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients","paper_url":"/paper/easy-ensemble-augmented-shot-y-shaped","paper_date":"2022-01-24","arxiv_id":"2201.09699","code_links":[{"title":"ybendou/easy","url":"https://github.com/ybendou/easy"},{"title":"brain-bzh/pefsl","url":"https://github.com/brain-bzh/pefsl"},{"title":"ybendou/fs-generalization","url":"https://github.com/ybendou/fs-generalization"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-2","slug":"few-shot-image-classification-on-fc100-5-way-2","dataset":"FC100 5-way (10-shot)","dataset_url":"/dataset/fc100","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MTL","paper_title":"Meta-Transfer Learning for Few-Shot Learning","paper_url":"/paper/meta-transfer-learning-for-few-shot-learning","paper_date":"2018-12-06","arxiv_id":"1812.02391","code_links":[{"title":"yaoyao-liu/meta-transfer-learning","url":"https://github.com/yaoyao-liu/meta-transfer-learning"},{"title":"yaoyao-liu/mini-imagenet-tools","url":"https://github.com/yaoyao-liu/mini-imagenet-tools"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-fewshot","slug":"few-shot-image-classification-on-fewshot","dataset":"Fewshot-CIFAR100 - 1-Shot Learning","dataset_url":"/dataset/fc100","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"pseudo-shots","paper_title":"Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks","paper_url":"/paper/pseudo-shots-few-shot-learning-with-auxiliary","paper_date":"2020-12-13","arxiv_id":"2012.07176","code_links":[{"title":"BatsResearch/efsl","url":"https://github.com/BatsResearch/efsl"},{"title":"Reza-esfandiarpoor/pseudo-shots","url":"https://github.com/Reza-esfandiarpoor/pseudo-shots"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-fewshot-1","slug":"few-shot-image-classification-on-fewshot-1","dataset":"Fewshot-CIFAR100 - 5-Shot Learning","dataset_url":"/dataset/fc100","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"pseudo-shots","paper_title":"Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks","paper_url":"/paper/pseudo-shots-few-shot-learning-with-auxiliary","paper_date":"2020-12-13","arxiv_id":"2012.07176","code_links":[{"title":"BatsResearch/efsl","url":"https://github.com/BatsResearch/efsl"},{"title":"Reza-esfandiarpoor/pseudo-shots","url":"https://github.com/Reza-esfandiarpoor/pseudo-shots"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-flowers-102-1","slug":"few-shot-image-classification-on-flowers-102-1","dataset":"Flowers-102 - 0-Shot","dataset_url":"/dataset/oxford-102-flower","rows_in_archive":1,"metrics":["AP50","Accuracy"],"first_row_in_archive_order":{"model":"Word CNN-RNN (DS-SJE Embedding)","paper_title":"Learning Deep Representations of Fine-grained Visual Descriptions","paper_url":"/paper/learning-deep-representations-of-fine-grained","paper_date":"2016-05-17","arxiv_id":"1605.05395","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"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist","slug":"few-shot-image-classification-on-inaturalist","dataset":"iNaturalist (227-way multi-shot)","dataset_url":"/dataset/inaturalist","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LaplacianShot","paper_title":"Laplacian Regularized Few-Shot Learning","paper_url":"/paper/laplacian-regularized-few-shot-learning","paper_date":"2020-06-29","arxiv_id":"2006.15486","code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"imtiazziko/LaplacianShot","url":"https://github.com/imtiazziko/LaplacianShot"}],"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":7}}},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist-1","slug":"few-shot-image-classification-on-inaturalist-1","dataset":"iNaturalist 2018 - 1-shot","dataset_url":"/dataset/inaturalist","rows_in_archive":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MAWS (ViT-2B)","paper_title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","paper_url":"/paper/the-effectiveness-of-mae-pre-pretraining-for","paper_date":"2023-03-23","arxiv_id":"2303.13496","code_links":[{"title":"facebookresearch/maws","url":"https://github.com/facebookresearch/maws"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist-2","slug":"few-shot-image-classification-on-inaturalist-2","dataset":"iNaturalist 2018 - 5-shot","dataset_url":"/dataset/inaturalist","rows_in_archive":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MAWS (ViT-2B)","paper_title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","paper_url":"/paper/the-effectiveness-of-mae-pre-pretraining-for","paper_date":"2023-03-23","arxiv_id":"2303.13496","code_links":[{"title":"facebookresearch/maws","url":"https://github.com/facebookresearch/maws"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist-3","slug":"few-shot-image-classification-on-inaturalist-3","dataset":"iNaturalist 2018 - 10-shot","dataset_url":"/dataset/inaturalist","rows_in_archive":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MAWS (ViT-2B)","paper_title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","paper_url":"/paper/the-effectiveness-of-mae-pre-pretraining-for","paper_date":"2023-03-23","arxiv_id":"2303.13496","code_links":[{"title":"facebookresearch/maws","url":"https://github.com/facebookresearch/maws"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-mini-9","slug":"few-shot-image-classification-on-mini-9","dataset":"mini-ImageNet - 100-Way","dataset_url":"/dataset/mini-imagenet","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GCR","paper_title":"Few-Shot Learning with Global Class Representations","paper_url":"/paper/few-shot-learning-with-global-class","paper_date":"2019-08-14","arxiv_id":"1908.05257","code_links":[{"title":"tiangeluo/fsl-global","url":"https://github.com/tiangeluo/fsl-global"},{"title":"huang-research-group/globalfsl2019","url":"https://github.com/huang-research-group/globalfsl2019"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/few-shot-image-classification-on-miniimagenet-1","slug":"few-shot-image-classification-on-miniimagenet-1","dataset":"miniImagenet → CUB (5-way 1-shot)","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LaplacianShot","paper_title":"Laplacian Regularized Few-Shot Learning","paper_url":"/paper/laplacian-regularized-few-shot-learning","paper_date":"2020-06-29","arxiv_id":"2006.15486","code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"imtiazziko/LaplacianShot","url":"https://github.com/imtiazziko/LaplacianShot"}],"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":7}}},{"leaderboard":"/sota/few-shot-image-classification-on-miniimagenet-2","slug":"few-shot-image-classification-on-miniimagenet-2","dataset":"miniImagenet → CUB (5-way 5-shot)","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LaplacianShot","paper_title":"Laplacian Regularized Few-Shot Learning","paper_url":"/paper/laplacian-regularized-few-shot-learning","paper_date":"2020-06-29","arxiv_id":"2006.15486","code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"imtiazziko/LaplacianShot","url":"https://github.com/imtiazziko/LaplacianShot"}],"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":7}}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-4","slug":"few-shot-image-classification-on-omniglot-1-4","dataset":"OMNIGLOT - 1-Shot, 423 way","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"APL","paper_title":"Adaptive Posterior Learning: few-shot learning with a surprise-based memory module","paper_url":"/paper/adaptive-posterior-learning-few-shot-learning","paper_date":"2019-02-07","arxiv_id":"1902.02527","code_links":[{"title":"cogentlabs/apl","url":"https://github.com/cogentlabs/apl"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-5","slug":"few-shot-image-classification-on-omniglot-1-5","dataset":"OMNIGLOT - 1-Shot, 1000 way","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"APL","paper_title":"Adaptive Posterior Learning: few-shot learning with a surprise-based memory module","paper_url":"/paper/adaptive-posterior-learning-few-shot-learning","paper_date":"2019-02-07","arxiv_id":"1902.02527","code_links":[{"title":"cogentlabs/apl","url":"https://github.com/cogentlabs/apl"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-4","slug":"few-shot-image-classification-on-omniglot-5-4","dataset":"OMNIGLOT - 5-Shot, 423 way","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"APL","paper_title":"Adaptive Posterior Learning: few-shot learning with a surprise-based memory module","paper_url":"/paper/adaptive-posterior-learning-few-shot-learning","paper_date":"2019-02-07","arxiv_id":"1902.02527","code_links":[{"title":"cogentlabs/apl","url":"https://github.com/cogentlabs/apl"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-5","slug":"few-shot-image-classification-on-omniglot-5-5","dataset":"OMNIGLOT - 5-Shot, 1000 way","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"APL","paper_title":"Adaptive Posterior Learning: few-shot learning with a surprise-based memory module","paper_url":"/paper/adaptive-posterior-learning-few-shot-learning","paper_date":"2019-02-07","arxiv_id":"1902.02527","code_links":[{"title":"cogentlabs/apl","url":"https://github.com/cogentlabs/apl"}],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-oxford-102","slug":"few-shot-image-classification-on-oxford-102","dataset":"Oxford 102 Flower","dataset_url":"/dataset/oxford-102-flower","rows_in_archive":1,"metrics":["ACCURACY"],"first_row_in_archive_order":{"model":"RS-FSL","paper_title":"Rich Semantics Improve Few-shot Learning","paper_url":"/paper/rich-semantics-improve-few-shot-learning","paper_date":"2021-04-26","arxiv_id":"2104.12709","code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-image-classification-on-ut-zappos50k","slug":"few-shot-image-classification-on-ut-zappos50k","dataset":"UT Zappos50K","dataset_url":"/dataset/ut-zappos50k","rows_in_archive":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MScon","paper_title":"Multi-Similarity Contrastive Learning","paper_url":"/paper/multi-similarity-contrastive-learning","paper_date":"2023-07-06","arxiv_id":"2307.02712","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/mini-imagenet","name":"mini-Imagenet","full_name":"","num_papers_in_archive":1345},{"url":"/dataset/oxford-102-flower","name":"Oxford 102 Flower","full_name":"102 Category Flower Dataset","num_papers_in_archive":1307},{"url":"/dataset/stanford-cars","name":"Stanford Cars","full_name":"","num_papers_in_archive":790},{"url":"/dataset/inaturalist","name":"iNaturalist","full_name":"","num_papers_in_archive":603},{"url":"/dataset/caltech-256","name":"Caltech-256","full_name":"","num_papers_in_archive":401},{"url":"/dataset/tieredimagenet","name":"tieredImageNet","full_name":"tieredImageNet","num_papers_in_archive":317},{"url":"/dataset/awa-1","name":"AwA","full_name":"Animals with Attributes","num_papers_in_archive":264},{"url":"/dataset/awa2-1","name":"AwA2","full_name":"Animals with Attributes 2","num_papers_in_archive":231},{"url":"/dataset/cifar-fs","name":"CIFAR-FS","full_name":"CIFAR100 few-shots","num_papers_in_archive":206},{"url":"/dataset/apy","name":"aPY","full_name":"Attribute Pascal and Yahoo","num_papers_in_archive":147},{"url":"/dataset/fc100","name":"FC100","full_name":"Fewshot-CIFAR100","num_papers_in_archive":137},{"url":"/dataset/meta-dataset","name":"Meta-Dataset","full_name":"","num_papers_in_archive":128},{"url":"/dataset/stanford-dogs","name":"Stanford Dogs","full_name":"Stanford Dogs","num_papers_in_archive":57},{"url":"/dataset/ut-zappos50k","name":"UT Zappos50K","full_name":"","num_papers_in_archive":32},{"url":"/dataset/sun","name":"SUN","full_name":"SUN Database","num_papers_in_archive":31},{"url":"/dataset/bongard-hoi","name":"Bongard-HOI","full_name":"","num_papers_in_archive":12},{"url":"/dataset/artbench-10","name":"ArtBench-10 (32x32)","full_name":"","num_papers_in_archive":7},{"url":"/dataset/orbit","name":"ORBIT","full_name":"","num_papers_in_archive":7},{"url":"/dataset/fewsol","name":"FewSOL","full_name":"A Dataset for Few-Shot Object Learning in Robotic Environments","num_papers_in_archive":4},{"url":"/dataset/mineralimage5k","name":"MineralImage5k","full_name":"Benchmark for 5k raw mineral species recognition","num_papers_in_archive":1},{"url":"/dataset/omni-image","name":"Omni-Image","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/generalized-few-shot-classification","name":"Generalized Few-Shot Classification"},{"url":"/task/unsupervised-few-shot-image-classification","name":"Unsupervised Few-Shot Image Classification"},{"url":"/task/unsupervised-few-shot-learning","name":"Unsupervised Few-Shot Learning"}],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":220,"tagged_in_all":353,"items":[{"url":"/paper/model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","arxiv_id":"1703.03400","repositories_listed":85,"syntology":{"n":154,"n_ran":86,"n_unverified":68,"n_pointer_only":57}},{"url":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","repositories_listed":82,"syntology":{"n":20,"n_ran":16,"n_unverified":4,"n_pointer_only":16}},{"url":"/paper/prototypical-networks-for-few-shot-learning","title":"Prototypical Networks for Few-shot Learning","date":"2017-03-15","arxiv_id":"1703.05175","repositories_listed":43,"syntology":{"n":64,"n_ran":49,"n_unverified":15,"n_pointer_only":18}},{"url":"/paper/matching-networks-for-one-shot-learning","title":"Matching Networks for One Shot Learning","date":"2016-06-13","arxiv_id":"1606.04080","repositories_listed":26,"syntology":{"n":16,"n_ran":6,"n_unverified":10,"n_pointer_only":6}},{"url":"/paper/meta-dataset-a-dataset-of-datasets-for","title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","date":"2019-03-07","arxiv_id":"1903.03096","repositories_listed":15,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/on-first-order-meta-learning-algorithms","title":"On First-Order Meta-Learning Algorithms","date":"2018-03-08","arxiv_id":"1803.02999","repositories_listed":13,"syntology":{"n":42,"n_ran":24,"n_unverified":18,"n_pointer_only":13}},{"url":"/paper/learning-to-compare-relation-network-for-few","title":"Learning to Compare: Relation Network for Few-Shot Learning","date":"2017-11-16","arxiv_id":"1711.06025","repositories_listed":13,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/how-to-train-your-maml","title":"How to train your MAML","date":"2018-10-22","arxiv_id":"1810.09502","repositories_listed":10,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/elevater-a-benchmark-and-toolkit-for","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","date":"2022-04-19","arxiv_id":"2204.08790","repositories_listed":9,"syntology":{"n":20,"n_ran":4,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/set-transformer-a-framework-for-attention","title":"Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks","date":"2018-10-01","arxiv_id":"1810.00825","repositories_listed":9,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/charting-the-right-manifold-manifold-mixup","title":"Charting the Right Manifold: Manifold Mixup for Few-shot Learning","date":"2019-07-28","arxiv_id":"1907.12087","repositories_listed":8,"syntology":null},{"url":"/paper/meta-learning-with-differentiable-convex","title":"Meta-Learning with Differentiable Convex Optimization","date":"2019-04-07","arxiv_id":"1904.03758","repositories_listed":7,"syntology":null},{"url":"/paper/leveraging-the-feature-distribution-in","title":"Leveraging the Feature Distribution in Transfer-based Few-Shot Learning","date":"2020-06-06","arxiv_id":"2006.03806","repositories_listed":6,"syntology":{"n":26,"n_ran":10,"n_unverified":16,"n_pointer_only":11}},{"url":"/paper/simpleshot-revisiting-nearest-neighbor","title":"SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning","date":"2019-11-12","arxiv_id":"1911.04623","repositories_listed":6,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/meta-learning-with-implicit-gradients","title":"Meta-Learning with Implicit Gradients","date":"2019-09-10","arxiv_id":"1909.04630","repositories_listed":6,"syntology":{"n":36,"n_ran":27,"n_unverified":9,"n_pointer_only":10}},{"url":"/paper/learning-embedding-adaptation-for-few-shot","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","date":"2018-12-10","arxiv_id":"1812.03664","repositories_listed":6,"syntology":null},{"url":"/paper/pangu-a-large-scale-autoregressive-pretrained","title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","date":"2021-04-26","arxiv_id":"2104.12369","repositories_listed":5,"syntology":null},{"url":"/paper/universal-representation-learning-from","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","date":"2021-03-25","arxiv_id":"2103.13841","repositories_listed":5,"syntology":{"n":26,"n_ran":12,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/deepemd-few-shot-image-classification-with","title":"DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning","date":"2020-03-15","arxiv_id":"2003.06777","repositories_listed":5,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/towards-a-neural-statistician","title":"Towards a Neural Statistician","date":"2016-06-07","arxiv_id":"1606.02185","repositories_listed":5,"syntology":{"n":14,"n_ran":2,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/comparing-the-efficacy-of-fine-tuning-and","title":"Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation","date":"2023-06-23","arxiv_id":"2306.13554","repositories_listed":4,"syntology":null},{"url":"/paper/improving-protonet-for-few-shot-video-object","title":"Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022","date":"2022-10-01","arxiv_id":"2210.00174","repositories_listed":4,"syntology":null},{"url":"/paper/self-supervision-can-be-a-good-few-shot","title":"Self-Supervision Can Be a Good Few-Shot Learner","date":"2022-07-19","arxiv_id":"2207.09176","repositories_listed":4,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/improving-task-adaptation-for-cross-domain","title":"Cross-domain Few-shot Learning with Task-specific Adapters","date":"2021-07-01","arxiv_id":"2107.00358","repositories_listed":4,"syntology":null},{"url":"/paper/harnessing-the-power-of-infinitely-wide-deep-1","title":"Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks","date":"2019-10-03","arxiv_id":"1910.01663","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/edge-labeling-graph-neural-network-for-few","title":"Edge-labeling Graph Neural Network for Few-shot Learning","date":"2019-05-04","arxiv_id":"1905.01436","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/dynamic-few-shot-visual-learning-without","title":"Dynamic Few-Shot Visual Learning without Forgetting","date":"2018-04-25","arxiv_id":"1804.09458","repositories_listed":4,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/a-simple-neural-attentive-meta-learner","title":"A Simple Neural Attentive Meta-Learner","date":"2017-07-11","arxiv_id":"1707.03141","repositories_listed":4,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/low-shot-visual-recognition-by-shrinking-and","title":"Low-shot Visual Recognition by Shrinking and Hallucinating Features","date":"2016-06-09","arxiv_id":"1606.02819","repositories_listed":4,"syntology":null},{"url":"/paper/meta-album-multi-domain-meta-dataset-for-few-1","title":"Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification","date":"2023-02-16","arxiv_id":"2302.08909","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}],"syntology_records":22,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}