{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/conditional-channel-gated-networks-for-task","title":"Conditional Channel Gated Networks for Task-Aware Continual Learning","arxiv_id":"2004.00070","date":"2020-03-31","proceeding":"CVPR 2020 6","authors":["Davide Abati","Jakub Tomczak","Tijmen Blankevoort","Simone Calderara","Rita Cucchiara","Babak Ehteshami Bejnordi"],"abstract":"Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this work, we introduce a novel framework to tackle this problem with conditional computation. We equip each convolutional layer with task-specific gating modules, selecting which filters to apply on the given input. This way, we achieve two appealing properties. Firstly, the execution patterns of the gates allow to identify and protect important filters, ensuring no loss in the performance of the model for previously learned tasks. Secondly, by using a sparsity objective, we can promote the selection of a limited set of kernels, allowing to retain sufficient model capacity to digest new tasks.Existing solutions require, at test time, awareness of the task to which each example belongs to. This knowledge, however, may not be available in many practical scenarios. Therefore, we additionally introduce a task classifier that predicts the task label of each example, to deal with settings in which a task oracle is not available. We validate our proposal on four continual learning datasets. Results show that our model consistently outperforms existing methods both in the presence and the absence of a task oracle. Notably, on Split SVHN and Imagenet-50 datasets, our model yields up to 23.98% and 17.42% improvement in accuracy w.r.t. competing methods.","url_abs":"https://arxiv.org/abs/2004.00070v1","url_pdf":"https://arxiv.org/pdf/2004.00070v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"conditional-channel-gated-networks-for-task","repo_url":"https://github.com/lit-leo/cgate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-learning-on-imagenet-50-5-tasks","task":"Continual Learning","dataset":"ImageNet-50 (5 tasks)","model":"CCGN","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"35.24"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2004.00070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00070"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lit-leo/cgate","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7b63a04724226238","entry":"convert_to_layerwise_stat","repo":"lit-leo/cgate","repo_kind":"listed","path":"src/visualization.py","file_url":"https://github.com/lit-leo/cgate/blob/HEAD/src/visualization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b63a04724226238"}},{"code_sha256_prefix":"fc08404570af13c6","entry":"extract_taskwise_stat","repo":"lit-leo/cgate","repo_kind":"listed","path":"src/visualization.py","file_url":"https://github.com/lit-leo/cgate/blob/HEAD/src/visualization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc08404570af13c6"}},{"code_sha256_prefix":"f3ca9493477db598","entry":"get_coreset_loader","repo":"lit-leo/cgate","repo_kind":"listed","path":"src/data.py","file_url":"https://github.com/lit-leo/cgate/blob/HEAD/src/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3ca9493477db598"}},{"code_sha256_prefix":"de186ee17852ec67","entry":"get_loaders","repo":"lit-leo/cgate","repo_kind":"listed","path":"src/data.py","file_url":"https://github.com/lit-leo/cgate/blob/HEAD/src/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de186ee17852ec67"}},{"code_sha256_prefix":"e0f0ddbe7f79c547","entry":"gumbel_sigmoid","repo":"lit-leo/cgate","repo_kind":"listed","path":"src/blocks.py","file_url":"https://github.com/lit-leo/cgate/blob/HEAD/src/blocks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0f0ddbe7f79c547"}},{"code_sha256_prefix":"9dce6d4bf3b88343","entry":"prepare_dataset","repo":"lit-leo/cgate","repo_kind":"listed","path":"src/data.py","file_url":"https://github.com/lit-leo/cgate/blob/HEAD/src/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9dce6d4bf3b88343"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}