{"url":"/sota/incremental-learning-on-cifar-100-b0-5steps","task":{"name":"Incremental Learning","url":"/task/incremental-learning","note":null},"dataset":{"name":"CIFAR-100-B0(5steps of 20 classes)","url":null},"category":"Methodology","categories":["Methodology"],"category_note":null,"description":"Incremental learning aims to develop artificially intelligent systems that can continuously learn to address new tasks from new data while preserving knowledge learned from previously learned tasks.","description_from":"task","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":["Average Incremental Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average Incremental Accuracy":"higher"}},"counts":{"rows":10,"rows_with_code":10,"rows_with_paper_page":10,"rows_dated":10,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"View-Batch(TCIL)","metrics":{"Average Incremental Accuracy":"79.23"},"uses_additional_data":false,"paper_date":"2025-03-24","paper":"/paper/do-your-best-and-get-enough-rest-for","paper_url":"https://arxiv.org/abs/2503.18371v1","paper_title":"Do Your Best and Get Enough Rest for Continual Learning","code":"https://github.com/hankyul2/viewbatchmodel","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"TCIL","metrics":{"Average Incremental Accuracy":"77.72"},"uses_additional_data":false,"paper_date":"2022-12-29","paper":"/paper/resolving-task-confusion-in-dynamic-expansion","paper_url":"https://arxiv.org/abs/2212.14284v2","paper_title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","code":"https://github.com/yellowpancake/tcil","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"TCIL-Lite","metrics":{"Average Incremental Accuracy":"76.96"},"uses_additional_data":false,"paper_date":"2022-12-29","paper":"/paper/resolving-task-confusion-in-dynamic-expansion","paper_url":"https://arxiv.org/abs/2212.14284v2","paper_title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","code":"https://github.com/yellowpancake/tcil","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"DER(w/o P)","metrics":{"Average Incremental Accuracy":"76.80"},"uses_additional_data":false,"paper_date":"2021-03-31","paper":"/paper/der-dynamically-expandable-representation-for","paper_url":"https://arxiv.org/abs/2103.16788v1","paper_title":"DER: Dynamically Expandable Representation for Class Incremental Learning","code":"https://github.com/g-u-n/pycil","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"BiC","metrics":{"Average Incremental Accuracy":"73.10"},"uses_additional_data":false,"paper_date":"2019-05-30","paper":"/paper/large-scale-incremental-learning-1","paper_url":"https://arxiv.org/abs/1905.13260v1","paper_title":"Large Scale Incremental Learning","code":"https://github.com/ContinualAI/avalanche","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"WA","metrics":{"Average Incremental Accuracy":"72.81"},"uses_additional_data":false,"paper_date":"2019-11-16","paper":"/paper/maintaining-discrimination-and-fairness-in","paper_url":"https://arxiv.org/abs/1911.07053v1","paper_title":"Maintaining Discrimination and Fairness in Class Incremental Learning","code":"https://github.com/g-u-n/pycil","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"iCaRL","metrics":{"Average Incremental Accuracy":"71.14"},"uses_additional_data":false,"paper_date":"2016-11-23","paper":"/paper/icarl-incremental-classifier-and","paper_url":"http://arxiv.org/abs/1611.07725v2","paper_title":"iCaRL: Incremental Classifier and Representation Learning","code":"https://github.com/ContinualAI/avalanche","n_code_links":10,"syntology":{"n_ran":3,"n_unverified":11,"n_samples":14,"n_pointer_only_licence":3}},{"rank_in_archive_order":8,"model":"RPSNet","metrics":{"Average Incremental Accuracy":"70.50"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/random-path-selection-for-incremental","paper_url":"https://arxiv.org/abs/1906.01120v3","paper_title":"An Adaptive Random Path Selection Approach for Incremental Learning","code":"https://github.com/brjathu/RPSnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"PODNet","metrics":{"Average Incremental Accuracy":"66.70"},"uses_additional_data":false,"paper_date":"2020-04-28","paper":"/paper/small-task-incremental-learning","paper_url":"https://arxiv.org/abs/2004.13513v3","paper_title":"PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning","code":"https://github.com/g-u-n/pycil","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"UCIR","metrics":{"Average Incremental Accuracy":"62.77"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/learning-a-unified-classifier-incrementally","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Hou_Learning_a_Unified_Classifier_Incrementally_via_Rebalancing_CVPR_2019_paper.html","paper_title":"Learning a Unified Classifier Incrementally via Rebalancing","code":"https://github.com/aimagelab/mammoth","n_code_links":3,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":10,"n_unverified":16,"n_samples":26,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":10,"n_unverified":16,"n_samples":26,"n_pointer_only_licence":4,"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"}}}