{"url":"/task/continual-learning","name":"Continual Learning","slug":"continual-learning","description_markdown":"**Continual Learning** (also known as **Incremental Learning**, **Life-long Learning**) is a concept to learn a model for a large number of tasks sequentially without forgetting knowledge obtained from the preceding tasks, where the data in the old tasks are not available anymore during training new ones.  \r\nIf not mentioned, the benchmarks here are **Task-CL**, where task-id is provided on validation.\r\n\r\nSource:  \r\n[Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation](https://arxiv.org/abs/1908.02984)  \r\n[Three scenarios for continual learning](https://arxiv.org/abs/1904.07734)  \r\n[Lifelong Machine Learning](https://books.google.ca/books/about/Lifelong_Machine_Learning.html?id=JQ5pDwAAQBAJ&redir_esc=y)  \r\n[Continual lifelong learning with neural networks: A review](https://www.sciencedirect.com/science/article/pii/S0893608019300231)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2644,"papers_with_code":1142,"benchmarks":33,"benchmark_tables_in_archive":33,"benchmark_tables_shown":33,"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":35,"subtasks":5,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/continual-learning-on-asc-19-tasks","slug":"continual-learning-on-asc-19-tasks","dataset":"ASC (19 tasks)","dataset_url":"/dataset/asc-til-19-tasks","rows_in_archive":15,"metrics":["F1 - macro"],"first_row_in_archive_order":{"model":"Multi-task Learning (MTL; Upper Bound)","paper_title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","paper_url":"/paper/achieving-forgetting-prevention-and-knowledge-1","paper_date":"2021-12-05","arxiv_id":"2112.02706","code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-visual-domain-decathlon","slug":"continual-learning-on-visual-domain-decathlon","dataset":"visual domain decathlon (10 tasks)","dataset_url":"/dataset/visual-domain-decathlon","rows_in_archive":14,"metrics":["decathlon discipline (Score)","Avg. Accuracy"],"first_row_in_archive_order":{"model":"NetTailor","paper_title":"NetTailor: Tuning the Architecture, Not Just the Weights","paper_url":"/paper/nettailor-tuning-the-architecture-not-just-1","paper_date":"2019-06-29","arxiv_id":"1907.00274","code_links":[{"title":"pedro-morgado/nettailor","url":"https://github.com/pedro-morgado/nettailor"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-cifar100-20-tasks","slug":"continual-learning-on-cifar100-20-tasks","dataset":"Cifar100 (20 tasks)","dataset_url":"/dataset/cifar-100","rows_in_archive":9,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Model Zoo-Continual","paper_title":"Model Zoo: A Growing \"Brain\" That Learns Continually","paper_url":"/paper/boosting-a-model-zoo-for-multi-task-and","paper_date":"2021-06-06","arxiv_id":"2106.03027","code_links":[{"title":"grasp-lyrl/modelzoo_continual","url":"https://github.com/grasp-lyrl/modelzoo_continual"},{"title":"rahul13ramesh/modelzoo_continual","url":"https://github.com/rahul13ramesh/modelzoo_continual"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continual-learning-on-tiny-imagenet-10tasks","slug":"continual-learning-on-tiny-imagenet-10tasks","dataset":"Tiny-ImageNet (10tasks)","dataset_url":null,"rows_in_archive":9,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"ALTA-ViTB/16","paper_title":"Cross-Modal Alternating Learning with Task-Aware Representations for Continual Learning","paper_url":"/paper/cross-modal-alternating-learning-with-task","paper_date":"2023-12-07","arxiv_id":null,"code_links":[{"title":"vijaylee/ALTA","url":"https://github.com/vijaylee/ALTA"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-f-celeba-10-tasks","slug":"continual-learning-on-f-celeba-10-tasks","dataset":"F-CelebA (10 tasks)","dataset_url":"/dataset/f-celeba-10-tasks","rows_in_archive":7,"metrics":["Acc"],"first_row_in_archive_order":{"model":"CAT (CNN backbone)","paper_title":"Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks","paper_url":"/paper/continual-learning-of-a-mixed-sequence-of-1","paper_date":"2021-12-18","arxiv_id":"2112.10017","code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"},{"title":"ZixuanKe/CAT","url":"https://github.com/ZixuanKe/CAT"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-20newsgroup-10-tasks","slug":"continual-learning-on-20newsgroup-10-tasks","dataset":"20Newsgroup (10 tasks)","dataset_url":"/dataset/20newsgroup-10-tasks","rows_in_archive":6,"metrics":["F1 - macro"],"first_row_in_archive_order":{"model":"CTR","paper_title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","paper_url":"/paper/achieving-forgetting-prevention-and-knowledge-1","paper_date":"2021-12-05","arxiv_id":"2112.02706","code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-cubs-fine-grained-6","slug":"continual-learning-on-cubs-fine-grained-6","dataset":"CUBS (Fine-grained 6 Tasks)","dataset_url":null,"rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CondConvContinual","paper_title":"EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING","paper_url":"/paper/extending-conditional-convolution-structures","paper_date":"2020-12-07","arxiv_id":null,"code_links":[{"title":"ivclab/CondConvContinual","url":"https://github.com/ivclab/CondConvContinual"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-dsc-10-tasks","slug":"continual-learning-on-dsc-10-tasks","dataset":"DSC (10 tasks)","dataset_url":"/dataset/dsc-10-tasks","rows_in_archive":6,"metrics":["F1 - macro"],"first_row_in_archive_order":{"model":"CTR","paper_title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","paper_url":"/paper/achieving-forgetting-prevention-and-knowledge-1","paper_date":"2021-12-05","arxiv_id":"2112.02706","code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-flowers-fine-grained-6","slug":"continual-learning-on-flowers-fine-grained-6","dataset":"Flowers (Fine-grained 6 Tasks)","dataset_url":"/dataset/oxford-102-flower","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CondConvContinual","paper_title":"EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING","paper_url":"/paper/extending-conditional-convolution-structures","paper_date":"2020-12-07","arxiv_id":null,"code_links":[{"title":"ivclab/CondConvContinual","url":"https://github.com/ivclab/CondConvContinual"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-imagenet-fine-grained-6","slug":"continual-learning-on-imagenet-fine-grained-6","dataset":"ImageNet (Fine-grained 6 Tasks)","dataset_url":null,"rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ProgressiveNet","paper_title":"Progressive Neural Networks","paper_url":"/paper/progressive-neural-networks","paper_date":"2016-06-15","arxiv_id":"1606.04671","code_links":[{"title":"ContinualAI/avalanche","url":"https://github.com/ContinualAI/avalanche"},{"title":"aimagelab/mammoth","url":"https://github.com/aimagelab/mammoth"},{"title":"arazd/ProgressivePrompts","url":"https://github.com/arazd/ProgressivePrompts"},{"title":"arcosin/Doric","url":"https://github.com/arcosin/Doric"},{"title":"feifeiobama/rewireneuron","url":"https://github.com/feifeiobama/rewireneuron"},{"title":"GuangpingYuan/PNN_Pong_A3C","url":"https://github.com/GuangpingYuan/PNN_Pong_A3C"},{"title":"geox-lab/cmn","url":"https://github.com/geox-lab/cmn"},{"title":"khashiii97/PNN","url":"https://github.com/khashiii97/PNN"},{"title":"khashiii97/Progressive-Neural-Networks-for-IDS","url":"https://github.com/khashiii97/Progressive-Neural-Networks-for-IDS"},{"title":"sarthakTUM/progressive-neural-networks-for-nlp","url":"https://github.com/sarthakTUM/progressive-neural-networks-for-nlp"},{"title":"imatge-upc/progressive_nns","url":"https://github.com/imatge-upc/progressive_nns"},{"title":"epsilon-deltta/ssd_guillotine","url":"https://github.com/epsilon-deltta/ssd_guillotine"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}}},{"leaderboard":"/sota/continual-learning-on-sketch-fine-grained-6","slug":"continual-learning-on-sketch-fine-grained-6","dataset":"Sketch (Fine-grained 6 Tasks)","dataset_url":"/dataset/sketch","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CondConvContinual","paper_title":"EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING","paper_url":"/paper/extending-conditional-convolution-structures","paper_date":"2020-12-07","arxiv_id":null,"code_links":[{"title":"ivclab/CondConvContinual","url":"https://github.com/ivclab/CondConvContinual"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-stanford-cars-fine","slug":"continual-learning-on-stanford-cars-fine","dataset":"Stanford Cars (Fine-grained 6 Tasks)","dataset_url":"/dataset/stanford-cars","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CPG","paper_title":"Compacting, Picking and Growing for Unforgetting Continual Learning","paper_url":"/paper/compacting-picking-and-growing-for","paper_date":"2019-10-15","arxiv_id":"1910.06562","code_links":[{"title":"ivclab/CPG","url":"https://github.com/ivclab/CPG"},{"title":"p0werweirdo/tagfcl","url":"https://github.com/p0werweirdo/tagfcl"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continual-learning-on-wikiart-fine-grained-6","slug":"continual-learning-on-wikiart-fine-grained-6","dataset":"Wikiart (Fine-grained 6 Tasks)","dataset_url":"/dataset/wikiart","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CondConvContinual","paper_title":"EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING","paper_url":"/paper/extending-conditional-convolution-structures","paper_date":"2020-12-07","arxiv_id":null,"code_links":[{"title":"ivclab/CondConvContinual","url":"https://github.com/ivclab/CondConvContinual"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-cifar100-10-tasks","slug":"continual-learning-on-cifar100-10-tasks","dataset":"Cifar100 (10 tasks)","dataset_url":null,"rows_in_archive":5,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"ALTA-ViTB/16","paper_title":"Cross-Modal Alternating Learning with Task-Aware Representations for Continual Learning","paper_url":"/paper/cross-modal-alternating-learning-with-task","paper_date":"2023-12-07","arxiv_id":null,"code_links":[{"title":"vijaylee/ALTA","url":"https://github.com/vijaylee/ALTA"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-imagenet-50-5-tasks","slug":"continual-learning-on-imagenet-50-5-tasks","dataset":"ImageNet-50 (5 tasks)","dataset_url":null,"rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RMN","paper_title":"Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping","paper_url":"/paper/understanding-catastrophic-forgetting-and","paper_date":"2021-02-22","arxiv_id":"2102.11343","code_links":[{"title":"prakhark2/relevance-mapping-networks","url":"https://gitlab.com/prakhark2/relevance-mapping-networks"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-permuted-mnist","slug":"continual-learning-on-permuted-mnist","dataset":"Permuted MNIST","dataset_url":"/dataset/permuted-mnist","rows_in_archive":3,"metrics":["Average Accuracy","MLP Hidden Layers-width","Pretrained/Transfer Learning","BWT"],"first_row_in_archive_order":{"model":"RMN","paper_title":"Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping","paper_url":"/paper/understanding-catastrophic-forgetting-and","paper_date":"2021-02-22","arxiv_id":"2102.11343","code_links":[{"title":"prakhark2/relevance-mapping-networks","url":"https://gitlab.com/prakhark2/relevance-mapping-networks"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-split-cifar-100","slug":"continual-learning-on-split-cifar-100","dataset":"split CIFAR-100","dataset_url":null,"rows_in_archive":2,"metrics":["Average Accuracy","BWT"],"first_row_in_archive_order":{"model":"CODE-CL","paper_title":"CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning","paper_url":"/paper/code-cl-conceptor-based-gradient-projection","paper_date":"2024-11-21","arxiv_id":"2411.15235","code_links":[{"title":"mapolinario94/CODE-CL","url":"https://github.com/mapolinario94/CODE-CL"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-5-dataset-1-epoch","slug":"continual-learning-on-5-dataset-1-epoch","dataset":"5-dataset - 1 epoch","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TAG-RMSProp","paper_title":"TAG: Task-based Accumulated Gradients for Lifelong learning","paper_url":"/paper/tag-task-based-accumulated-gradients-for","paper_date":"2021-05-11","arxiv_id":"2105.05155","code_links":[{"title":"pranshu28/TAG","url":"https://github.com/pranshu28/TAG"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-5-datasets","slug":"continual-learning-on-5-datasets","dataset":"5-Datasets","dataset_url":null,"rows_in_archive":1,"metrics":["Average Accuracy","BWT"],"first_row_in_archive_order":{"model":"CODE-CL","paper_title":"CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning","paper_url":"/paper/code-cl-conceptor-based-gradient-projection","paper_date":"2024-11-21","arxiv_id":"2411.15235","code_links":[{"title":"mapolinario94/CODE-CL","url":"https://github.com/mapolinario94/CODE-CL"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-aids","slug":"continual-learning-on-aids","dataset":"AIDS","dataset_url":"/dataset/aids","rows_in_archive":1,"metrics":["1:3 Accuracy"],"first_row_in_archive_order":{"model":"TEST","paper_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","paper_url":"/paper/advances-and-challenges-in-foundation-agents","paper_date":"2025-03-31","arxiv_id":"2504.01990","code_links":[{"title":"foundationagents/awesome-foundation-agents","url":"https://github.com/foundationagents/awesome-foundation-agents"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-cifar-100-alexnet-300","slug":"continual-learning-on-cifar-100-alexnet-300","dataset":"CIFAR-100 AlexNet - 300 Epoch","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"IBM","paper_title":"Towards Redundancy-Free Sub-networks in Continual Learning","paper_url":"/paper/towards-redundancy-free-sub-networks-in","paper_date":"2023-12-01","arxiv_id":"2312.00840","code_links":[{"title":"zackschen/IBM-Net","url":"https://github.com/zackschen/IBM-Net"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-cifar-100-resnet-18-300","slug":"continual-learning-on-cifar-100-resnet-18-300","dataset":"CIFAR-100 ResNet-18 - 300 Epochs","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"IBM","paper_title":"Towards Redundancy-Free Sub-networks in Continual Learning","paper_url":"/paper/towards-redundancy-free-sub-networks-in","paper_date":"2023-12-01","arxiv_id":"2312.00840","code_links":[{"title":"zackschen/IBM-Net","url":"https://github.com/zackschen/IBM-Net"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-cifar100-20-tasks-1","slug":"continual-learning-on-cifar100-20-tasks-1","dataset":"Cifar100 (20 tasks) - 1 epoch","dataset_url":null,"rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"TAG-RMSProp","paper_title":"TAG: Task-based Accumulated Gradients for Lifelong learning","paper_url":"/paper/tag-task-based-accumulated-gradients-for","paper_date":"2021-05-11","arxiv_id":"2105.05155","code_links":[{"title":"pranshu28/TAG","url":"https://github.com/pranshu28/TAG"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-coarse-cifar100","slug":"continual-learning-on-coarse-cifar100","dataset":"Coarse-CIFAR100","dataset_url":null,"rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Model Zoo-Continual","paper_title":"Model Zoo: A Growing \"Brain\" That Learns Continually","paper_url":"/paper/boosting-a-model-zoo-for-multi-task-and","paper_date":"2021-06-06","arxiv_id":"2106.03027","code_links":[{"title":"grasp-lyrl/modelzoo_continual","url":"https://github.com/grasp-lyrl/modelzoo_continual"},{"title":"rahul13ramesh/modelzoo_continual","url":"https://github.com/rahul13ramesh/modelzoo_continual"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continual-learning-on-cub-200-2011-20-tasks-1","slug":"continual-learning-on-cub-200-2011-20-tasks-1","dataset":"CUB-200-2011 (20 tasks) - 1 epoch","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TAG-RMSProp","paper_title":"TAG: Task-based Accumulated Gradients for Lifelong learning","paper_url":"/paper/tag-task-based-accumulated-gradients-for","paper_date":"2021-05-11","arxiv_id":"2105.05155","code_links":[{"title":"pranshu28/TAG","url":"https://github.com/pranshu28/TAG"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-mini-imagenet-20-tasks","slug":"continual-learning-on-mini-imagenet-20-tasks","dataset":"mini-Imagenet (20 tasks) - 1 epoch","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TAG-RMSProp","paper_title":"TAG: Task-based Accumulated Gradients for Lifelong learning","paper_url":"/paper/tag-task-based-accumulated-gradients-for","paper_date":"2021-05-11","arxiv_id":"2105.05155","code_links":[{"title":"pranshu28/TAG","url":"https://github.com/pranshu28/TAG"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-miniimagenet","slug":"continual-learning-on-miniimagenet","dataset":"miniImagenet","dataset_url":"/dataset/mini-imagenet","rows_in_archive":1,"metrics":["Average Accuracy","BWT"],"first_row_in_archive_order":{"model":"CODE-CL","paper_title":"CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning","paper_url":"/paper/code-cl-conceptor-based-gradient-projection","paper_date":"2024-11-21","arxiv_id":"2411.15235","code_links":[{"title":"mapolinario94/CODE-CL","url":"https://github.com/mapolinario94/CODE-CL"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-miniimagenet-resnet-18","slug":"continual-learning-on-miniimagenet-resnet-18","dataset":"MiniImageNet ResNet-18 - 300 Epochs","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"IBM","paper_title":"Towards Redundancy-Free Sub-networks in Continual Learning","paper_url":"/paper/towards-redundancy-free-sub-networks-in","paper_date":"2023-12-01","arxiv_id":"2312.00840","code_links":[{"title":"zackschen/IBM-Net","url":"https://github.com/zackschen/IBM-Net"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-mlt17","slug":"continual-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}},{"leaderboard":"/sota/continual-learning-on-rotated-mnist","slug":"continual-learning-on-rotated-mnist","dataset":"Rotated MNIST","dataset_url":"/dataset/mnist","rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Model Zoo-Continual","paper_title":"Model Zoo: A Growing \"Brain\" That Learns Continually","paper_url":"/paper/boosting-a-model-zoo-for-multi-task-and","paper_date":"2021-06-06","arxiv_id":"2106.03027","code_links":[{"title":"grasp-lyrl/modelzoo_continual","url":"https://github.com/grasp-lyrl/modelzoo_continual"},{"title":"rahul13ramesh/modelzoo_continual","url":"https://github.com/rahul13ramesh/modelzoo_continual"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continual-learning-on-split-cifar-10-5-tasks","slug":"continual-learning-on-split-cifar-10-5-tasks","dataset":"Split CIFAR-10 (5 tasks)","dataset_url":"/dataset/cifar-10","rows_in_archive":1,"metrics":["Top 1 Accuracy %"],"first_row_in_archive_order":{"model":"H$^{2}$","paper_title":"Helpful or Harmful: Inter-Task Association in Continual Learning","paper_url":"/paper/helpful-or-harmful-inter-task-association-in","paper_date":"2022-10-23","arxiv_id":null,"code_links":[{"title":"Jin0316/Helpful-or-Harmful-Inter-Task-Association","url":"https://github.com/Jin0316/Helpful-or-Harmful-Inter-Task-Association"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-split-mnist-5-tasks","slug":"continual-learning-on-split-mnist-5-tasks","dataset":"Split MNIST (5 tasks)","dataset_url":null,"rows_in_archive":1,"metrics":["Top 1 Accuracy %"],"first_row_in_archive_order":{"model":"H$^{2}$","paper_title":"Helpful or Harmful: Inter-Task Association in Continual Learning","paper_url":"/paper/helpful-or-harmful-inter-task-association-in","paper_date":"2022-10-23","arxiv_id":null,"code_links":[{"title":"Jin0316/Helpful-or-Harmful-Inter-Task-Association","url":"https://github.com/Jin0316/Helpful-or-Harmful-Inter-Task-Association"}],"syntology":null}},{"leaderboard":"/sota/continual-learning-on-tinyimagenet-resnet-18","slug":"continual-learning-on-tinyimagenet-resnet-18","dataset":"TinyImageNet ResNet-18 - 300 Epochs","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"IBM","paper_title":"Towards Redundancy-Free Sub-networks in Continual Learning","paper_url":"/paper/towards-redundancy-free-sub-networks-in","paper_date":"2023-12-01","arxiv_id":"2312.00840","code_links":[{"title":"zackschen/IBM-Net","url":"https://github.com/zackschen/IBM-Net"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/mini-imagenet","name":"mini-Imagenet","full_name":"","num_papers_in_archive":1345},{"url":"/dataset/oxford-102-flower","name":"Oxford 102 Flower","full_name":"102 Category Flower Dataset","num_papers_in_archive":1307},{"url":"/dataset/stanford-cars","name":"Stanford Cars","full_name":"","num_papers_in_archive":790},{"url":"/dataset/sketch","name":"Sketch","full_name":"","num_papers_in_archive":237},{"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/wikiart","name":"WikiArt","full_name":"","num_papers_in_archive":96},{"url":"/dataset/aids","name":"AIDS","full_name":"AIDS","num_papers_in_archive":67},{"url":"/dataset/road","name":"ROAD","full_name":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","num_papers_in_archive":27},{"url":"/dataset/tweetqa","name":"TweetQA","full_name":"","num_papers_in_archive":19},{"url":"/dataset/continual-world","name":"Continual World","full_name":"","num_papers_in_archive":15},{"url":"/dataset/20newsgroup-10-tasks","name":"20Newsgroup (10 tasks)","full_name":"","num_papers_in_archive":11},{"url":"/dataset/asc-til-19-tasks","name":"ASC (TIL, 19 tasks)","full_name":"Task Incremental Aspect Sentiment Classification","num_papers_in_archive":11},{"url":"/dataset/lreid","name":"LReID","full_name":"","num_papers_in_archive":8},{"url":"/dataset/visual-domain-decathlon","name":"Visual Domain Decathlon","full_name":"Visual Domain Decathlon","num_papers_in_archive":8},{"url":"/dataset/dsc-10-tasks","name":"DSC (10 tasks)","full_name":"Task Incremental Document Sentiment Classification","num_papers_in_archive":6},{"url":"/dataset/f-celeba-10-tasks","name":"F-CelebA (10 tasks)","full_name":"Federated-CelebA (10 tasks)","num_papers_in_archive":6},{"url":"/dataset/wild-time","name":"Wild-Time","full_name":"","num_papers_in_archive":6},{"url":"/dataset/temporalwiki","name":"TemporalWiki","full_name":"","num_papers_in_archive":4},{"url":"/dataset/hasy","name":"HASY","full_name":"","num_papers_in_archive":3},{"url":"/dataset/mlt17","name":"MLT17","full_name":"","num_papers_in_archive":3},{"url":"/dataset/uestc-mmea-cl","name":"UESTC-MMEA-CL","full_name":"A multi-modal egocentric activity dataset for continual learning","num_papers_in_archive":3},{"url":"/dataset/invar-100","name":"InVar-100","full_name":"Industrial Objects in Varied Contexts","num_papers_in_archive":2},{"url":"/dataset/openloris-object","name":"OpenLORIS-object","full_name":"","num_papers_in_archive":2},{"url":"/dataset/skill-102","name":"SKILL-102","full_name":"SKILL 102 Lifelong Learning Dataset","num_papers_in_archive":2},{"url":"/dataset/begin-1","name":"BeGin","full_name":"","num_papers_in_archive":1},{"url":"/dataset/concon-dataset","name":"ConCon Dataset","full_name":"Continually Confounded Dataset","num_papers_in_archive":1},{"url":"/dataset/crl-person","name":"CRL-Person","full_name":"","num_papers_in_archive":1},{"url":"/dataset/hows","name":"HOWS","full_name":"HOWS-CL-25","num_papers_in_archive":1},{"url":"/dataset/idsprites","name":"idsprites","full_name":"Infinite dSprites","num_papers_in_archive":1},{"url":"/dataset/spot-10","name":"SPOT-10","full_name":"Animal Pattern Benchmark Dataset for Machine Learning Algorithms","num_papers_in_archive":1},{"url":"/dataset/tirod","name":"TiROD","full_name":"Tiny Robotics Object Detection","num_papers_in_archive":1}],"subtasks":[{"url":"/task/class-incremental-learning","name":"Class Incremental Learning"},{"url":"/task/continual-named-entity-recognition","name":"Continual Named Entity Recognition"},{"url":"/task/continual-panoptic-segmentation","name":"Continual Panoptic Segmentation"},{"url":"/task/tirod","name":"TiROD"},{"url":"/task/unsupervised-class-incremental-learning","name":"unsupervised class-incremental learning"}],"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":1142,"tagged_in_all":2644,"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/progressive-neural-networks","title":"Progressive Neural Networks","date":"2016-06-15","arxiv_id":"1606.04671","repositories_listed":12,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/190600695","title":"Continual learning with hypernetworks","date":"2019-06-03","arxiv_id":"1906.00695","repositories_listed":9,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"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/variational-continual-learning","title":"Variational Continual Learning","date":"2017-10-29","arxiv_id":"1710.10628","repositories_listed":8,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":3}},{"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/meta-learning-representations-for-continual","title":"Meta-Learning Representations for Continual Learning","date":"2019-05-29","arxiv_id":"1905.12588","repositories_listed":6,"syntology":null},{"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/continual-learning-through-synaptic","title":"Continual Learning Through Synaptic Intelligence","date":"2017-03-13","arxiv_id":"1703.04200","repositories_listed":6,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/blenderbot-3-a-deployed-conversational-agent","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","date":"2022-08-05","arxiv_id":"2208.03188","repositories_listed":5,"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/dataset-condensation-with-gradient-matching","title":"Dataset Condensation with Gradient Matching","date":"2020-06-10","arxiv_id":"2006.05929","repositories_listed":5,"syntology":null},{"url":"/paper/learning-to-continually-learn","title":"Learning to Continually Learn","date":"2020-02-21","arxiv_id":"2002.09571","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"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/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/generative-replay-with-feedback-connections","title":"Generative replay with feedback connections as a general strategy for continual learning","date":"2018-09-27","arxiv_id":"1809.10635","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/dataset-condensation-with-distribution","title":"Dataset Condensation with Distribution Matching","date":"2021-10-08","arxiv_id":"2110.04181","repositories_listed":4,"syntology":null},{"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/learning-to-continuously-optimize-wireless","title":"Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment","date":"2020-11-16","arxiv_id":"2011.07782","repositories_listed":4,"syntology":null},{"url":"/paper/understanding-the-role-of-training-regimes-in","title":"Understanding the Role of Training Regimes in Continual Learning","date":"2020-06-12","arxiv_id":"2006.06958","repositories_listed":4,"syntology":{"n":20,"n_ran":2,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/training-binary-neural-networks-using-the","title":"Training Binary Neural Networks using the Bayesian Learning Rule","date":"2020-02-25","arxiv_id":"2002.10778","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/radial-bayesian-neural-networks-robust","title":"Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning","date":"2019-07-01","arxiv_id":"1907.00865","repositories_listed":4,"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":2}},{"url":"/paper/packnet-adding-multiple-tasks-to-a-single","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","date":"2017-11-15","arxiv_id":"1711.05769","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"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/cat-balanced-continual-graph-learning-with","title":"CaT: Balanced Continual Graph Learning with Graph Condensation","date":"2023-09-18","arxiv_id":"2309.09455","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"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/continual-training-of-language-models-for-few","title":"Continual Training of Language Models for Few-Shot Learning","date":"2022-10-11","arxiv_id":"2210.05549","repositories_listed":3,"syntology":null}],"syntology_records":16,"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"}}