{"url":"/task/incremental-learning","name":"Incremental Learning","slug":"incremental-learning","description_markdown":"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.","categories":[{"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":1371,"papers_with_code":542,"benchmarks":22,"benchmark_tables_in_archive":22,"benchmark_tables_shown":22,"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":8,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes-3","slug":"incremental-learning-on-cifar-100-50-classes-3","dataset":"CIFAR-100 - 50 classes + 5 steps of 10 classes","dataset_url":"/dataset/cifar-100","rows_in_archive":15,"metrics":["Average Incremental Accuracy","Final Accuracy"],"first_row_in_archive_order":{"model":"TCIL","paper_title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","paper_url":"/paper/resolving-task-confusion-in-dynamic-expansion","paper_date":"2022-12-29","arxiv_id":"2212.14284","code_links":[{"title":"yellowpancake/tcil","url":"https://github.com/yellowpancake/tcil"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes-2","slug":"incremental-learning-on-cifar-100-50-classes-2","dataset":"CIFAR-100 - 50 classes + 10 steps of 5 classes","dataset_url":"/dataset/cifar-100","rows_in_archive":13,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"TCIL","paper_title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","paper_url":"/paper/resolving-task-confusion-in-dynamic-expansion","paper_date":"2022-12-29","arxiv_id":"2212.14284","code_links":[{"title":"yellowpancake/tcil","url":"https://github.com/yellowpancake/tcil"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-imagenet100-10-steps","slug":"incremental-learning-on-imagenet100-10-steps","dataset":"ImageNet100 - 10 steps","dataset_url":null,"rows_in_archive":13,"metrics":["Average Incremental Accuracy","Final Accuracy","Average Incremental Accuracy Top-5","Final Accuracy Top-5","# M Params"],"first_row_in_archive_order":{"model":"kNN-CLIP","paper_title":"Revisiting a kNN-based Image Classification System with High-capacity Storage","paper_url":"/paper/revisiting-a-knn-based-image-classification","paper_date":"2022-04-03","arxiv_id":"2204.01186","code_links":[],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-cifar-100-b0-5steps","slug":"incremental-learning-on-cifar-100-b0-5steps","dataset":"CIFAR-100-B0(5steps of 20 classes)","dataset_url":null,"rows_in_archive":10,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"View-Batch(TCIL)","paper_title":"Do Your Best and Get Enough Rest for Continual Learning","paper_url":"/paper/do-your-best-and-get-enough-rest-for","paper_date":"2025-03-24","arxiv_id":"2503.18371","code_links":[{"title":"hankyul2/viewbatchmodel","url":"https://github.com/hankyul2/viewbatchmodel"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-imagenet-10-steps","slug":"incremental-learning-on-imagenet-10-steps","dataset":"ImageNet - 10 steps","dataset_url":null,"rows_in_archive":10,"metrics":["Average Incremental Accuracy","Final Accuracy","Average Incremental Accuracy Top-5","Final Accuracy Top-5","# M Params"],"first_row_in_archive_order":{"model":"kNN-CLIP","paper_title":"Revisiting a kNN-based Image Classification System with High-capacity Storage","paper_url":"/paper/revisiting-a-knn-based-image-classification","paper_date":"2022-04-03","arxiv_id":"2204.01186","code_links":[],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-cifar100-b0-10steps","slug":"incremental-learning-on-cifar100-b0-10steps","dataset":"CIFAR100-B0(10steps of 10 classes)","dataset_url":null,"rows_in_archive":6,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"View-Batch(DER)","paper_title":"Do Your Best and Get Enough Rest for Continual Learning","paper_url":"/paper/do-your-best-and-get-enough-rest-for","paper_date":"2025-03-24","arxiv_id":"2503.18371","code_links":[{"title":"hankyul2/viewbatchmodel","url":"https://github.com/hankyul2/viewbatchmodel"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes-1","slug":"incremental-learning-on-cifar-100-50-classes-1","dataset":"CIFAR-100 - 50 classes + 25 steps of 2 classes","dataset_url":"/dataset/cifar-100","rows_in_archive":5,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"D3Former","paper_title":"D3Former: Debiased Dual Distilled Transformer for Incremental Learning","paper_url":"/paper/textrm-d-3-textrm-former-debiased-dual","paper_date":"2022-07-25","arxiv_id":"2208.00777","code_links":[{"title":"abdohelmy/D-3Former","url":"https://github.com/abdohelmy/D-3Former"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-cifar100b020step","slug":"incremental-learning-on-cifar100b020step","dataset":"CIFAR100B020Step(5ClassesPerStep)","dataset_url":null,"rows_in_archive":5,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"View-Batch(DER)","paper_title":"Do Your Best and Get Enough Rest for Continual Learning","paper_url":"/paper/do-your-best-and-get-enough-rest-for","paper_date":"2025-03-24","arxiv_id":"2503.18371","code_links":[{"title":"hankyul2/viewbatchmodel","url":"https://github.com/hankyul2/viewbatchmodel"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-imagenet-100-50-2","slug":"incremental-learning-on-imagenet-100-50-2","dataset":"ImageNet-100 - 50 classes + 10 steps of 5 classes","dataset_url":null,"rows_in_archive":5,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"RMM (ResNet-18)","paper_title":"RMM: Reinforced Memory Management for Class-Incremental Learning","paper_url":"/paper/rmm-reinforced-memory-management-for-class-1","paper_date":"2023-01-14","arxiv_id":"2301.05792","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"aimagelab/mammoth","url":"https://github.com/aimagelab/mammoth"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm/"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/incremental-learning-on-imagenet-100-50-3","slug":"incremental-learning-on-imagenet-100-50-3","dataset":"ImageNet-100 - 50 classes + 5 steps of 10 classes","dataset_url":null,"rows_in_archive":5,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"FOSTER","paper_title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","paper_url":"/paper/foster-feature-boosting-and-compression-for","paper_date":"2022-04-10","arxiv_id":"2204.04662","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"G-U-N/ECCV22-FOSTER","url":"https://github.com/G-U-N/ECCV22-FOSTER"}],"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes-4","slug":"incremental-learning-on-cifar-100-50-classes-4","dataset":"CIFAR-100 - 50 classes + 2 steps of 25 classes","dataset_url":null,"rows_in_archive":4,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"TCIL","paper_title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","paper_url":"/paper/resolving-task-confusion-in-dynamic-expansion","paper_date":"2022-12-29","arxiv_id":"2212.14284","code_links":[{"title":"yellowpancake/tcil","url":"https://github.com/yellowpancake/tcil"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-imagenet-500-classes-1","slug":"incremental-learning-on-imagenet-500-classes-1","dataset":"ImageNet - 500 classes + 5 steps of 100 classes","dataset_url":null,"rows_in_archive":4,"metrics":["Average Incremental Accuracy","Final Accuracy"],"first_row_in_archive_order":{"model":"RMM (ResNet-18)","paper_title":"RMM: Reinforced Memory Management for Class-Incremental Learning","paper_url":"/paper/rmm-reinforced-memory-management-for-class-1","paper_date":"2023-01-14","arxiv_id":"2301.05792","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"aimagelab/mammoth","url":"https://github.com/aimagelab/mammoth"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm/"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/incremental-learning-on-imagenet-500-classes-2","slug":"incremental-learning-on-imagenet-500-classes-2","dataset":"ImageNet - 500 classes + 10 steps of 50 classes","dataset_url":null,"rows_in_archive":4,"metrics":["Average Incremental Accuracy","Final Accuracy"],"first_row_in_archive_order":{"model":"RMM (ResNet-18)","paper_title":"RMM: Reinforced Memory Management for Class-Incremental Learning","paper_url":"/paper/rmm-reinforced-memory-management-for-class-1","paper_date":"2023-01-14","arxiv_id":"2301.05792","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"aimagelab/mammoth","url":"https://github.com/aimagelab/mammoth"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm/"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/incremental-learning-on-imagenet-100-50-1","slug":"incremental-learning-on-imagenet-100-50-1","dataset":"ImageNet-100 - 50 classes + 25 steps of 2 classes","dataset_url":null,"rows_in_archive":3,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"RMM (ResNet-18)","paper_title":"RMM: Reinforced Memory Management for Class-Incremental Learning","paper_url":"/paper/rmm-reinforced-memory-management-for-class-1","paper_date":"2023-01-14","arxiv_id":"2301.05792","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"aimagelab/mammoth","url":"https://github.com/aimagelab/mammoth"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm/"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/incremental-learning-on-cifar-100-50-classes","slug":"incremental-learning-on-cifar-100-50-classes","dataset":"CIFAR-100 - 50 classes + 50 steps of 1 class","dataset_url":"/dataset/cifar-100","rows_in_archive":2,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"PODNet","paper_title":"PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning","paper_url":"/paper/small-task-incremental-learning","paper_date":"2020-04-28","arxiv_id":"2004.13513","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"arthurdouillard/incremental_learning.pytorch","url":"https://github.com/arthurdouillard/incremental_learning.pytorch"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-imagenet-100-50","slug":"incremental-learning-on-imagenet-100-50","dataset":"ImageNet-100 - 50 classes + 50 steps of 1 class","dataset_url":null,"rows_in_archive":2,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"PODNet","paper_title":"PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning","paper_url":"/paper/small-task-incremental-learning","paper_date":"2020-04-28","arxiv_id":"2004.13513","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"arthurdouillard/incremental_learning.pytorch","url":"https://github.com/arthurdouillard/incremental_learning.pytorch"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-cifar-100-40-classes","slug":"incremental-learning-on-cifar-100-40-classes","dataset":"CIFAR-100 - 40 classes + 60 steps of 1 class (Exemplar-free)","dataset_url":null,"rows_in_archive":1,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"FeTrIL","paper_title":"FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning","paper_url":"/paper/fetril-feature-translation-for-exemplar-free","paper_date":"2022-11-23","arxiv_id":"2211.13131","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"gregoirepetit/fetril","url":"https://github.com/gregoirepetit/fetril"}],"syntology":null}},{"leaderboard":"/sota/incremental-learning-on-cifar100b050s","slug":"incremental-learning-on-cifar100b050s","dataset":"CIFAR100B050S(2ClassesPerStep)","dataset_url":null,"rows_in_archive":1,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"DER(ResNet-18)","paper_title":"DER: Dynamically Expandable Representation for Class Incremental Learning","paper_url":"/paper/der-dynamically-expandable-representation-for","paper_date":"2021-03-31","arxiv_id":"2103.16788","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"Rhyssiyan/DER-ClassIL.pytorch","url":"https://github.com/Rhyssiyan/DER-ClassIL.pytorch"}],"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/incremental-learning-on-imagenet-10k-5225","slug":"incremental-learning-on-imagenet-10k-5225","dataset":"ImageNet-10k - 5225 classes + 5 steps of 1045 classes","dataset_url":null,"rows_in_archive":1,"metrics":["Final Accuracy"],"first_row_in_archive_order":{"model":"PPCA-CLIP","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/incremental-learning-on-imagenet-500-classes-3","slug":"incremental-learning-on-imagenet-500-classes-3","dataset":"ImageNet - 500 classes + 25 steps of 20 classes","dataset_url":null,"rows_in_archive":1,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"RMM (ResNet-18)","paper_title":"RMM: Reinforced Memory Management for Class-Incremental Learning","paper_url":"/paper/rmm-reinforced-memory-management-for-class-1","paper_date":"2023-01-14","arxiv_id":"2301.05792","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"aimagelab/mammoth","url":"https://github.com/aimagelab/mammoth"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm/"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/incremental-learning-on-imagenet100-20-steps","slug":"incremental-learning-on-imagenet100-20-steps","dataset":"ImageNet100 - 20 steps","dataset_url":null,"rows_in_archive":1,"metrics":["Average Incremental Accuracy"],"first_row_in_archive_order":{"model":"FOSTER","paper_title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","paper_url":"/paper/foster-feature-boosting-and-compression-for","paper_date":"2022-04-10","arxiv_id":"2204.04662","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"G-U-N/ECCV22-FOSTER","url":"https://github.com/G-U-N/ECCV22-FOSTER"}],"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/incremental-learning-on-mlt17","slug":"incremental-learning-on-mlt17","dataset":"MLT17","dataset_url":"/dataset/mlt17","rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"MRM","paper_title":"MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition","paper_url":"/paper/mrn-multiplexed-routing-network-for","paper_date":"2023-05-24","arxiv_id":"2305.14758","code_links":[{"title":"simplify23/MRN","url":"https://github.com/simplify23/MRN"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/core50","name":"CORe50","full_name":"","num_papers_in_archive":132},{"url":"/dataset/permuted-mnist","name":"Permuted MNIST","full_name":"","num_papers_in_archive":121},{"url":"/dataset/toplogo-10","name":"TopLogo-10","full_name":"","num_papers_in_archive":6},{"url":"/dataset/mlt17","name":"MLT17","full_name":"","num_papers_in_archive":3},{"url":"/dataset/concept-1k","name":"Concept-1K","full_name":"Concept-1K","num_papers_in_archive":1},{"url":"/dataset/hows","name":"HOWS","full_name":"HOWS-CL-25","num_papers_in_archive":1},{"url":"/dataset/incremental-dialog-dataset","name":"Incremental Dialog Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":542,"tagged_in_all":1371,"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/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/gradient-episodic-memory-for-continual","title":"Gradient Episodic Memory for Continual Learning","date":"2017-06-26","arxiv_id":"1706.08840","repositories_listed":7,"syntology":null},{"url":"/paper/end-to-end-incremental-learning","title":"End-to-End Incremental Learning","date":"2018-07-25","arxiv_id":"1807.09536","repositories_listed":6,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"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/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/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/cost-effective-active-learning-for-deep-image","title":"Cost-Effective Active Learning for Deep Image Classification","date":"2017-01-13","arxiv_id":"1701.03551","repositories_listed":4,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":2}},{"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/casper-latent-spectral-regularization-for","title":"Latent Spectral Regularization for Continual Learning","date":"2023-01-09","arxiv_id":"2301.03345","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/visual-memorability-for-robotic","title":"Visual Memorability for Robotic Interestingness via Unsupervised Online Learning","date":"2020-05-18","arxiv_id":"2005.08829","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/incremental-learning-of-object-detectors","title":"Incremental Learning of Object Detectors without Catastrophic Forgetting","date":"2017-08-23","arxiv_id":"1708.06977","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"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/boosting-continual-learning-of-vision","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","date":"2024-03-18","arxiv_id":"2403.11549","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"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},{"url":"/paper/incremental-sequence-labeling-a-tale-of-two","title":"Incremental Sequence Labeling: A Tale of Two Shifts","date":"2024-02-16","arxiv_id":"2402.10447","repositories_listed":2,"syntology":null},{"url":"/paper/concept-1k-a-novel-benchmark-for-instance","title":"Can LLMs Learn New Concepts Incrementally without Forgetting?","date":"2024-02-13","arxiv_id":"2402.08526","repositories_listed":2,"syntology":null},{"url":"/paper/cascaded-scaling-classifier-class-incremental","title":"Class incremental learning with probability dampening and cascaded gated classifier","date":"2024-02-02","arxiv_id":"2402.01262","repositories_listed":2,"syntology":null},{"url":"/paper/federated-class-incremental-learning-with-new","title":"Federated Class-Incremental Learning with New-Class Augmented Self-Distillation","date":"2024-01-01","arxiv_id":"2401.00622","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"}}