{"url":"/sota/class-incremental-learning-on-cifar100","task":{"name":"Class Incremental Learning","url":"/task/class-incremental-learning","note":null},"dataset":{"name":"cifar100","url":"/dataset/cifar-100"},"category":"Computer Vision","categories":["Computer Vision","Methodology"],"category_note":null,"description":"Incremental learning of a sequence of tasks when the task-ID is not available at test time.","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":["10-stage 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":{"10-stage average accuracy":"higher"}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"S&B","metrics":{"10-stage average accuracy":"68.18"},"uses_additional_data":false,"paper_date":"2021-07-03","paper":"/paper/split-and-bridge-adaptable-class-incremental","paper_url":"https://arxiv.org/abs/2107.01349v1","paper_title":"Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network","code":"https://github.com/bigdata-inha/Split-and-Bridge","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":2,"model":"SCR","metrics":{"10-stage average accuracy":"65.98"},"uses_additional_data":false,"paper_date":"2020-04-23","paper":"/paper/supervised-contrastive-learning","paper_url":"https://arxiv.org/abs/2004.11362v5","paper_title":"Supervised Contrastive Learning","code":"https://github.com/google-research/google-research/tree/master/supcon","n_code_links":26,"syntology":{"n_ran":6,"n_unverified":17,"n_samples":23,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"iCaRL","metrics":{"10-stage average accuracy":"63.24"},"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":4,"model":"LUCIR","metrics":{"10-stage average accuracy":"56.53"},"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},{"rank_in_archive_order":5,"model":"ABD","metrics":{"10-stage average accuracy":"54.44"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/always-be-dreaming-a-new-approach-for-data","paper_url":"https://arxiv.org/abs/2106.09701v2","paper_title":"Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning","code":"https://github.com/GT-RIPL/AlwaysBeDreaming-DFCIL","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"EMR","metrics":{"10-stage average accuracy":"48.66"},"uses_additional_data":false,"paper_date":"2019-02-27","paper":"/paper/continual-learning-with-tiny-episodic","paper_url":"https://arxiv.org/abs/1902.10486v4","paper_title":"On Tiny Episodic Memories in Continual Learning","code":"https://github.com/ContinualAI/avalanche","n_code_links":6,"syntology":null},{"rank_in_archive_order":7,"model":"A-GEM","metrics":{"10-stage average accuracy":"45.76"},"uses_additional_data":false,"paper_date":"2018-12-02","paper":"/paper/efficient-lifelong-learning-with-a-gem","paper_url":"http://arxiv.org/abs/1812.00420v2","paper_title":"Efficient Lifelong Learning with A-GEM","code":"https://github.com/ContinualAI/avalanche","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":11,"n_samples":12,"n_pointer_only_licence":0}}],"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":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":16,"n_unverified":48,"n_samples":64,"n_pointer_only_licence":8,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":16,"n_unverified":48,"n_samples":64,"n_pointer_only_licence":8,"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"}}}