{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/easy-ensemble-augmented-shot-y-shaped","title":"EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients","arxiv_id":"2201.09699","date":"2022-01-24","proceeding":null,"authors":["Yassir Bendou","Yuqing Hu","Raphael Lafargue","Giulia Lioi","Bastien Pasdeloup","Stéphane Pateux","Vincent Gripon"],"abstract":"Few-shot learning aims at leveraging knowledge learned by one or more deep learning models, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available. Recent years have seen a fair number of works in the field, introducing methods with numerous ingredients. A frequent problem, though, is the use of suboptimally trained models to extract knowledge, leading to interrogations on whether proposed approaches bring gains compared to using better initial models without the introduced ingredients. In this work, we propose a simple methodology, that reaches or even beats state of the art performance on multiple standardized benchmarks of the field, while adding almost no hyperparameters or parameters to those used for training the initial deep learning models on the generic dataset. This methodology offers a new baseline on which to propose (and fairly compare) new techniques or adapt existing ones.","url_abs":"https://arxiv.org/abs/2201.09699v2","url_pdf":"https://arxiv.org/pdf/2201.09699v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"easy-ensemble-augmented-shot-y-shaped","repo_url":"https://github.com/ybendou/easy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"easy-ensemble-augmented-shot-y-shaped","repo_url":"https://github.com/brain-bzh/pefsl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"easy-ensemble-augmented-shot-y-shaped","repo_url":"https://github.com/ybendou/fs-generalization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (1-shot)","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":8,"of":38,"metrics":{"Accuracy":"87.16"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (1-shot)","model":"EASY 2xResNet12 1/√2 (transductive)","rank_in_archive_order":9,"of":38,"metrics":{"Accuracy":"86.99"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (1-shot)","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":22,"of":38,"metrics":{"Accuracy":"76.2"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (1-shot)","model":"EASY 2xResNet12 1/√2 (inductive)","rank_in_archive_order":25,"of":38,"metrics":{"Accuracy":"75.24"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (5-shot)","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":11,"of":39,"metrics":{"Accuracy":"90.47"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (5-shot)","model":"EASY 2xResNet12 1/√2 (transductive)","rank_in_archive_order":12,"of":39,"metrics":{"Accuracy":"90.2"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (5-shot)","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":16,"of":39,"metrics":{"Accuracy":"89.0"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (5-shot)","model":"EASY 2xResNet12 1/√2 (inductive)","rank_in_archive_order":21,"of":39,"metrics":{"Accuracy":"88.38"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-2","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"93.79"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":9,"of":36,"metrics":{"Accuracy":"90.56"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"EASY 4xResNet12 (transductive)","rank_in_archive_order":10,"of":36,"metrics":{"Accuracy":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":22,"of":36,"metrics":{"Accuracy":"78.56"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"EASY 4xResNet12 (inductive)","rank_in_archive_order":23,"of":36,"metrics":{"Accuracy":"77.97"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 5-shot","model":"EASY 4xResNet12 (transductive)","rank_in_archive_order":9,"of":32,"metrics":{"Accuracy":"93.5"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 5-shot","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":14,"of":32,"metrics":{"Accuracy":"91.93"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 5-shot","model":"EASY 4xResNet12 (inductive)","rank_in_archive_order":15,"of":32,"metrics":{"Accuracy":"91.59"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way","task":"Few-Shot Image Classification","dataset":"FC100 5-way (1-shot)","model":"EASY 2xResNet12 1/√2 (transductive)","rank_in_archive_order":2,"of":22,"metrics":{"Accuracy":"54.47"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way","task":"Few-Shot Image Classification","dataset":"FC100 5-way (1-shot)","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":3,"of":22,"metrics":{"Accuracy":"54.13"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way","task":"Few-Shot Image Classification","dataset":"FC100 5-way (1-shot)","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":8,"of":22,"metrics":{"Accuracy":"48.07"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way","task":"Few-Shot Image Classification","dataset":"FC100 5-way (1-shot)","model":"EASY 2xResNet12 1/√2 (inductive)","rank_in_archive_order":9,"of":22,"metrics":{"Accuracy":"47.94"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-1","task":"Few-Shot Image Classification","dataset":"FC100 5-way (5-shot)","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":5,"of":22,"metrics":{"Accuracy":"66.86"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-1","task":"Few-Shot Image Classification","dataset":"FC100 5-way (5-shot)","model":"EASY 2xResNet12 1/√2 (transductive)","rank_in_archive_order":8,"of":22,"metrics":{"Accuracy":"65.82"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-1","task":"Few-Shot Image Classification","dataset":"FC100 5-way (5-shot)","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":10,"of":22,"metrics":{"Accuracy":"64.74"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-1","task":"Few-Shot Image Classification","dataset":"FC100 5-way (5-shot)","model":"EASY 2xResNet12 1/√2 (inductive)","rank_in_archive_order":11,"of":22,"metrics":{"Accuracy":"64.14"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":10,"of":105,"metrics":{"Accuracy":"84.04"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"EASY 2xResNet12 1/√2 (transductive)","rank_in_archive_order":13,"of":105,"metrics":{"Accuracy":"82.31"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":30,"of":105,"metrics":{"Accuracy":"71.75"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"EASY 2xResNet12 1/√2 (inductive)","rank_in_archive_order":33,"of":105,"metrics":{"Accuracy":"70.63"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":14,"of":95,"metrics":{"Accuracy":"89.14"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"EASY 2xResNet12 1/√2 (transductive)","rank_in_archive_order":16,"of":95,"metrics":{"Accuracy":"88.57"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":18,"of":95,"metrics":{"Accuracy":"87.15"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"EASY 2xResNet12 1/√2 (inductive)","rank_in_archive_order":22,"of":95,"metrics":{"Accuracy":"86.28"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":6,"of":49,"metrics":{"Accuracy":"84.29"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"ASY ResNet12 (transductive)","rank_in_archive_order":8,"of":49,"metrics":{"Accuracy":"83.98"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":19,"of":49,"metrics":{"Accuracy":"74.71"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"ASY ResNet12 (ours)","rank_in_archive_order":21,"of":49,"metrics":{"Accuracy":"74.31"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-1","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"EASY 3xResNet12 (transductive)","rank_in_archive_order":9,"of":51,"metrics":{"Accuracy":"89.76"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-1","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"ASY ResNet12 (transductive)","rank_in_archive_order":11,"of":51,"metrics":{"Accuracy":"89.26"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-1","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"EASY 3xResNet12 (inductive)","rank_in_archive_order":15,"of":51,"metrics":{"Accuracy":"88.33"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-1","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"ASY ResNet12 (inductive)","rank_in_archive_order":17,"of":51,"metrics":{"Accuracy":"87.86"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-learning-on-mini-imagenet-5-way-1","task":"Few-Shot Learning","dataset":"Mini-Imagenet 5-way (1-shot)","model":"EASY (transductive)","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"82.75"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.09699","atlas_url":"https://app.syntology.ai/?focus=2201.09699","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2201.09699"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2201.09699\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2201.09699"},"call":"get_concepts_for_paper(arxiv_id=\"2201.09699\")"}],"by_repo":[{"repo":"ybendou/easy","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"brain-bzh/pefsl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ybendou/fs-generalization","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"efd8ca5d0ba0da2a87bee79c8dc0733e3dde543ae14a67d3ba1a02c3bc971f30","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}