{"url":"/sota/few-shot-class-incremental-learning-on-mini","task":{"name":"Few-Shot Class-Incremental Learning","url":"/task/few-shot-class-incremental-learning","note":null},"dataset":{"name":"mini-Imagenet","url":"/dataset/mini-imagenet"},"category":"Computer Vision","categories":["Computer Vision","Methodology"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Last Accuracy ","Average Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Last Accuracy ":"higher","Average Accuracy":"higher"}},"counts":{"rows":12,"rows_with_code":9,"rows_with_paper_page":12,"rows_dated":12,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CoACT","metrics":{"Last Accuracy ":"96.24"},"uses_additional_data":false,"paper_date":"2024-05-26","paper":"/paper/few-shot-tuning-of-foundation-models-for","paper_url":"https://arxiv.org/abs/2405.16625v1","paper_title":"Few-shot Tuning of Foundation Models for Class-incremental Learning","code":"https://github.com/shuvenduroy/coact-fscil","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"PriViLege","metrics":{"Average Accuracy":"95.27","Last Accuracy ":"94.10"},"uses_additional_data":false,"paper_date":"2024-04-02","paper":"/paper/pre-trained-vision-and-language-transformers","paper_url":"https://arxiv.org/abs/2404.02117v1","paper_title":"Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners","code":"https://github.com/khu-agi/privilege","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":2,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"SV-T","metrics":{"Average Accuracy":"85.07","Last Accuracy ":"81.65"},"uses_additional_data":false,"paper_date":"2023-03-27","paper":"/paper/semantic-visual-guided-transformer-for-few","paper_url":"https://arxiv.org/abs/2303.15494v1","paper_title":"Semantic-visual Guided Transformer for Few-shot Class-incremental Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"BOT","metrics":{"Last Accuracy ":"59.57"},"uses_additional_data":false,"paper_date":"2024-03-21","paper":"/paper/a-bag-of-tricks-for-few-shot-class","paper_url":"https://arxiv.org/abs/2403.14392v2","paper_title":"A Bag of Tricks for Few-Shot Class-Incremental Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"NC-FSCIL","metrics":{"Average Accuracy":"67.82","Last Accuracy ":"58.31"},"uses_additional_data":false,"paper_date":"2023-02-02","paper":"/paper/neural-collapse-inspired-feature-classifier","paper_url":"https://openreview.net/forum?id=y5W8tpojhtJ","paper_title":"Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning","code":"https://github.com/NeuralCollapseApplications/FSCIL","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"C-FSCIL","metrics":{"Average Accuracy":"61.61","Last Accuracy ":"51.41"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/constrained-few-shot-class-incremental","paper_url":"https://arxiv.org/abs/2203.16588v1","paper_title":"Constrained Few-shot Class-incremental Learning","code":"https://github.com/ibm/constrained-fscil","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"FACT","metrics":{"Average Accuracy":"60.70","Last Accuracy ":"50.49"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/forward-compatible-few-shot-class-incremental","paper_url":"https://arxiv.org/abs/2203.06953v1","paper_title":"Forward Compatible Few-Shot Class-Incremental Learning","code":"https://github.com/zhoudw-zdw/cvpr22-fact","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"LIMIT","metrics":{"Average Accuracy":"59.06","Last Accuracy ":"49.19"},"uses_additional_data":false,"paper_date":"2022-03-31","paper":"/paper/few-shot-class-incremental-learning-by","paper_url":"https://arxiv.org/abs/2203.17030v2","paper_title":"Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks","code":"https://github.com/zhoudw-zdw/TPAMI-Limit","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"F2M","metrics":{"Average Accuracy":"54.89","Last Accuracy ":"47.84"},"uses_additional_data":false,"paper_date":"2021-10-30","paper":"/paper/overcoming-catastrophic-forgetting-in","paper_url":"https://arxiv.org/abs/2111.01549v2","paper_title":"Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima","code":"https://github.com/moukamisama/f2m","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"CEC","metrics":{"Average Accuracy":"57.74","Last Accuracy ":"47.63"},"uses_additional_data":false,"paper_date":"2021-04-07","paper":"/paper/few-shot-incremental-learning-with","paper_url":"https://arxiv.org/abs/2104.03047v1","paper_title":"Few-Shot Incremental Learning with Continually Evolved Classifiers","code":"https://github.com/icoz69/cec-cvpr2021","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"IDLVQ-C","metrics":{"Average Accuracy":"51.16","Last Accuracy ":"41.84"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/incremental-few-shot-learning-via-vector","paper_url":"https://openreview.net/forum?id=3SV-ZePhnZM","paper_title":"Incremental few-shot learning via vector quantization in deep embedded space","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"AL-MML","metrics":{"Average Accuracy":"39.64","Last Accuracy ":"24.42"},"uses_additional_data":false,"paper_date":"2020-04-23","paper":"/paper/few-shot-class-incremental-learning","paper_url":"https://arxiv.org/abs/2004.10956v2","paper_title":"Few-Shot Class-Incremental Learning","code":"https://github.com/xyutao/fscil","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":27,"n_unverified":12,"n_samples":39,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":27,"n_unverified":12,"n_samples":39,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}