{"url":"/task/class-incremental-learning","name":"Class Incremental Learning","slug":"class-incremental-learning","description_markdown":"Incremental learning of a sequence of tasks when the task-ID is not available at test time.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":634,"papers_with_code":296,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":1,"subtasks":3,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/class-incremental-learning-on-cifar100","slug":"class-incremental-learning-on-cifar100","dataset":"cifar100","dataset_url":"/dataset/cifar-100","rows_in_archive":7,"metrics":["10-stage average accuracy"],"first_row_in_archive_order":{"model":"S&B","paper_title":"Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network","paper_url":"/paper/split-and-bridge-adaptable-class-incremental","paper_date":"2021-07-03","arxiv_id":"2107.01349","code_links":[{"title":"bigdata-inha/Split-and-Bridge","url":"https://github.com/bigdata-inha/Split-and-Bridge"}],"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":5}}},{"leaderboard":"/sota/class-incremental-learning-on-cifar-100-50-1","slug":"class-incremental-learning-on-cifar-100-50-1","dataset":"CIFAR-100 - 50 classes + 10 steps of 5 classes","dataset_url":"/dataset/cifar-100","rows_in_archive":2,"metrics":["Final Accuracy"],"first_row_in_archive_order":{"model":"PPCA-SWSL","paper_title":"Scalable Learning with Incremental Probabilistic PCA","paper_url":"/paper/scalable-learning-with-incremental","paper_date":"2022-12-20","arxiv_id":null,"code_links":[{"title":"barbua/PPCA","url":"https://github.com/barbua/PPCA"}],"syntology":null}},{"leaderboard":"/sota/class-incremental-learning-on-cifar-100-50-2","slug":"class-incremental-learning-on-cifar-100-50-2","dataset":"CIFAR-100 - 50 classes + 5 steps of 10 classes","dataset_url":"/dataset/cifar-100","rows_in_archive":2,"metrics":["Final Accuracy"],"first_row_in_archive_order":{"model":"PPCA-SWSL","paper_title":"Scalable Learning with Incremental Probabilistic PCA","paper_url":"/paper/scalable-learning-with-incremental","paper_date":"2022-12-20","arxiv_id":null,"code_links":[{"title":"barbua/PPCA","url":"https://github.com/barbua/PPCA"}],"syntology":null}},{"leaderboard":"/sota/class-incremental-learning-on-cifar100-b0-10","slug":"class-incremental-learning-on-cifar100-b0-10","dataset":"Cifar100-B0(10 tasks)-no-exemplars","dataset_url":null,"rows_in_archive":1,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"SEED","paper_title":"Divide and not forget: Ensemble of selectively trained experts in Continual Learning","paper_url":"/paper/divide-and-not-forget-ensemble-of-selectively","paper_date":"2024-01-18","arxiv_id":"2401.10191","code_links":[{"title":"grypesc/seed","url":"https://github.com/grypesc/seed"}],"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/class-incremental-learning-on-cifar100-b0-20","slug":"class-incremental-learning-on-cifar100-b0-20","dataset":"Cifar100-B0(20 tasks)-no-exemplars","dataset_url":null,"rows_in_archive":1,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"SEED","paper_title":"Divide and not forget: Ensemble of selectively trained experts in Continual Learning","paper_url":"/paper/divide-and-not-forget-ensemble-of-selectively","paper_date":"2024-01-18","arxiv_id":"2401.10191","code_links":[{"title":"grypesc/seed","url":"https://github.com/grypesc/seed"}],"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/class-incremental-learning-on-cifar100-b0-50","slug":"class-incremental-learning-on-cifar100-b0-50","dataset":"CIFAR100-B0(50 tasks)-no-exemplars","dataset_url":null,"rows_in_archive":1,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"SEED","paper_title":"Divide and not forget: Ensemble of selectively trained experts in Continual Learning","paper_url":"/paper/divide-and-not-forget-ensemble-of-selectively","paper_date":"2024-01-18","arxiv_id":"2401.10191","code_links":[{"title":"grypesc/seed","url":"https://github.com/grypesc/seed"}],"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045}],"subtasks":[{"url":"/task/class-incremental-semantic-segmentation","name":"Class-Incremental Semantic Segmentation"},{"url":"/task/few-shot-class-incremental-learning","name":"Few-Shot Class-Incremental Learning"},{"url":"/task/non-exemplar-based-class-incremental-learning","name":"Non-exemplar-based Class Incremental Learning"}],"parent_tasks":[{"url":"/task/continual-learning","name":"Continual Learning"}],"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":296,"tagged_in_all":634,"items":[{"url":"/paper/overcoming-catastrophic-forgetting-in-neural","title":"Overcoming catastrophic forgetting in neural networks","date":"2016-12-02","arxiv_id":"1612.00796","repositories_listed":29,"syntology":{"n":22,"n_ran":14,"n_unverified":8,"n_pointer_only":4}},{"url":"/paper/supervised-contrastive-learning","title":"Supervised Contrastive Learning","date":"2020-04-23","arxiv_id":"2004.11362","repositories_listed":26,"syntology":{"n":23,"n_ran":6,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/learning-without-forgetting","title":"Learning without Forgetting","date":"2016-06-29","arxiv_id":"1606.09282","repositories_listed":12,"syntology":{"n":15,"n_ran":9,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/icarl-incremental-classifier-and","title":"iCaRL: Incremental Classifier and Representation Learning","date":"2016-11-23","arxiv_id":"1611.07725","repositories_listed":10,"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":3}},{"url":"/paper/three-scenarios-for-continual-learning","title":"Three scenarios for continual learning","date":"2019-04-15","arxiv_id":"1904.07734","repositories_listed":8,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/continual-learning-with-tiny-episodic","title":"On Tiny Episodic Memories in Continual Learning","date":"2019-02-27","arxiv_id":"1902.10486","repositories_listed":6,"syntology":null},{"url":"/paper/learning-to-prompt-for-continual-learning-1","title":"Learning to Prompt for Continual Learning","date":"2021-12-16","arxiv_id":"2112.08654","repositories_listed":5,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":10}},{"url":"/paper/fine-grained-continual-learning","title":"Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches","date":"2019-07-08","arxiv_id":"1907.03799","repositories_listed":5,"syntology":null},{"url":"/paper/large-scale-incremental-learning-1","title":"Large Scale Incremental Learning","date":"2019-05-30","arxiv_id":"1905.13260","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/online-continual-learning-with-no-task","title":"Gradient based sample selection for online continual learning","date":"2019-03-20","arxiv_id":"1903.08671","repositories_listed":5,"syntology":null},{"url":"/paper/continual-learning-with-deep-generative","title":"Continual Learning with Deep Generative Replay","date":"2017-05-24","arxiv_id":"1705.08690","repositories_listed":5,"syntology":null},{"url":"/paper/rmm-reinforced-memory-management-for-class-1","title":"RMM: Reinforced Memory Management for Class-Incremental Learning","date":"2023-01-14","arxiv_id":"2301.05792","repositories_listed":4,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/avalanche-an-end-to-end-library-for-continual","title":"Avalanche: an End-to-End Library for Continual Learning","date":"2021-04-01","arxiv_id":"2104.00405","repositories_listed":4,"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/a-simple-unified-framework-for-detecting-out","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","date":"2018-07-10","arxiv_id":"1807.03888","repositories_listed":4,"syntology":{"n":13,"n_ran":9,"n_unverified":4,"n_pointer_only":12}},{"url":"/paper/external-knowledge-injection-for-clip-based","title":"External Knowledge Injection for CLIP-Based Class-Incremental Learning","date":"2025-03-11","arxiv_id":"2503.08510","repositories_listed":3,"syntology":null},{"url":"/paper/fecam-exploiting-the-heterogeneity-of-class-1","title":"FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning","date":"2023-09-25","arxiv_id":"2309.14062","repositories_listed":3,"syntology":{"n":21,"n_ran":11,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/revisiting-class-incremental-learning-with","title":"Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need","date":"2023-03-13","arxiv_id":"2303.07338","repositories_listed":3,"syntology":null},{"url":"/paper/deep-class-incremental-learning-a-survey","title":"Class-Incremental Learning: A Survey","date":"2023-02-07","arxiv_id":"2302.03648","repositories_listed":3,"syntology":null},{"url":"/paper/a-multi-head-model-for-continual-learning-via","title":"A Multi-Head Model for Continual Learning via Out-of-Distribution Replay","date":"2022-08-20","arxiv_id":"2208.09734","repositories_listed":3,"syntology":null},{"url":"/paper/supervised-contrastive-replay-revisiting-the","title":"Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning","date":"2021-03-22","arxiv_id":"2103.13885","repositories_listed":3,"syntology":null},{"url":"/paper/gdumb-a-simple-approach-that-questions-our","title":"GDumb: A Simple Approach that Questions Our Progress in Continual Learning","date":"2020-08-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/dark-experience-for-general-continual","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","date":"2020-04-15","arxiv_id":"2004.07211","repositories_listed":3,"syntology":null},{"url":"/paper/learning-a-unified-classifier-incrementally","title":"Learning a Unified Classifier Incrementally via Rebalancing","date":"2019-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/efficient-lifelong-learning-with-a-gem","title":"Efficient Lifelong Learning with A-GEM","date":"2018-12-02","arxiv_id":"1812.00420","repositories_listed":3,"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/continuous-knowledge-preserving-decomposition","title":"Continuous Knowledge-Preserving Decomposition for Few-Shot Continual Learning","date":"2025-01-09","arxiv_id":"2501.05017","repositories_listed":2,"syntology":null},{"url":"/paper/mos-model-surgery-for-pre-trained-model-based","title":"MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning","date":"2024-12-12","arxiv_id":"2412.09441","repositories_listed":2,"syntology":{"n":17,"n_ran":6,"n_unverified":11,"n_pointer_only":12}},{"url":"/paper/air-analytic-imbalance-rectifier-for","title":"AIR: Analytic Imbalance Rectifier for Continual Learning","date":"2024-08-19","arxiv_id":"2408.10349","repositories_listed":2,"syntology":null},{"url":"/paper/data-free-generative-replay-for-class","title":"Data-Free Generative Replay for Class-Incremental Learning on Imbalanced Data","date":"2024-06-07","arxiv_id":"2406.09052","repositories_listed":2,"syntology":null},{"url":"/paper/g-acil-analytic-learning-for-exemplar-free","title":"GACL: Exemplar-Free Generalized Analytic Continual Learning","date":"2024-03-23","arxiv_id":"2403.15706","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/a-streamlined-approach-to-multimodal-few-shot","title":"A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets","date":"2024-03-10","arxiv_id":"2403.06295","repositories_listed":2,"syntology":null}],"syntology_records":14,"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"}}