{"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/compacting-picking-and-growing-for","title":"Compacting, Picking and Growing for Unforgetting Continual Learning","arxiv_id":"1910.06562","date":"2019-10-15","proceeding":"NeurIPS 2019 12","authors":["Steven C. Y. Hung","Cheng-Hao Tu","Cheng-En Wu","Chien-Hung Chen","Yi-Ming Chan","Chu-Song Chen"],"abstract":"Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the principles of deep model compression, critical weights selection, and progressive networks expansion. By enforcing their integration in an iterative manner, we introduce an incremental learning method that is scalable to the number of sequential tasks in a continual learning process. Our approach is easy to implement and owns several favorable characteristics. First, it can avoid forgetting (i.e., learn new tasks while remembering all previous tasks). Second, it allows model expansion but can maintain the model compactness when handling sequential tasks. Besides, through our compaction and selection/expansion mechanism, we show that the knowledge accumulated through learning previous tasks is helpful to build a better model for the new tasks compared to training the models independently with tasks. Experimental results show that our approach can incrementally learn a deep model tackling multiple tasks without forgetting, while the model compactness is maintained with the performance more satisfiable than individual task training.","url_abs":"https://arxiv.org/abs/1910.06562v3","url_pdf":"https://arxiv.org/pdf/1910.06562v3.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":"compacting-picking-and-growing-for","repo_url":"https://github.com/ivclab/CPG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"compacting-picking-and-growing-for","repo_url":"https://github.com/p0werweirdo/tagfcl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"age-and-gender-classification","task_name":"Age And Gender Classification"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":"facial-expression-recognition","task_name":"Facial Expression Recognition (FER)"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-and-gender-classification-on-adience-age","task":"Age And Gender Classification","dataset":"Adience Age","model":"CPG (single crop, pytorch)","rank_in_archive_order":10,"of":16,"metrics":{"Accuracy (5-fold)":"57.66"},"uses_additional_data":true},{"leaderboard":"/sota/age-and-gender-classification-on-adience","task":"Age And Gender Classification","dataset":"Adience Gender","model":"CPG (single crop, pytorch)","rank_in_archive_order":5,"of":10,"metrics":{"Accuracy (5-fold)":"89.66"},"uses_additional_data":true},{"leaderboard":"/sota/continual-learning-on-cubs-fine-grained-6","task":"Continual Learning","dataset":"CUBS (Fine-grained 6 Tasks)","model":"CPG","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"83.59"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-cifar100-20-tasks","task":"Continual Learning","dataset":"Cifar100 (20 tasks)","model":"CPG","rank_in_archive_order":5,"of":9,"metrics":{"Average Accuracy":"80.9"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-flowers-fine-grained-6","task":"Continual Learning","dataset":"Flowers (Fine-grained 6 Tasks)","model":"CPG","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"96.62"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-imagenet-fine-grained-6","task":"Continual Learning","dataset":"ImageNet (Fine-grained 6 Tasks)","model":"CPG","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"75.81"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-sketch-fine-grained-6","task":"Continual Learning","dataset":"Sketch (Fine-grained 6 Tasks)","model":"CPG","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"80.33"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-stanford-cars-fine","task":"Continual Learning","dataset":"Stanford Cars (Fine-grained 6 Tasks)","model":"CPG","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"92.80"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-wikiart-fine-grained-6","task":"Continual Learning","dataset":"Wikiart (Fine-grained 6 Tasks)","model":"CPG","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"77.15"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-affectnet","task":"Facial Expression Recognition (FER)","dataset":"AffectNet","model":"CPG","rank_in_archive_order":47,"of":50,"metrics":{"Accuracy (7 emotion)":"63.57"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.06562","atlas_url":"https://app.syntology.ai/?focus=1910.06562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06562"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ivclab/CPG","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/p0werweirdo/tagfcl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":1,"ran":1,"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":"d9def42110729a85","entry":"conv1x1","repo":"ivclab/CPG","repo_kind":"official","path":"packnet_models/resnet.py","file_url":"https://github.com/ivclab/CPG/blob/HEAD/packnet_models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"ivclab/CPG","repo_kind":"official","path":"packnet_models/resnet.py","file_url":"https://github.com/ivclab/CPG/blob/HEAD/packnet_models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"ffcfd7be7fccf20c","entry":"resnet_block","repo":"p0werweirdo/tagfcl","repo_kind":"listed","path":"src/models/ServerModel.py","file_url":"https://github.com/p0werweirdo/tagfcl/blob/HEAD/src/models/ServerModel.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ffcfd7be7fccf20c"}},{"code_sha256_prefix":"f12377e78b0616c2","entry":"resnet18","repo":"ivclab/CPG","repo_kind":"official","path":"packnet_models/resnet.py","file_url":"https://github.com/ivclab/CPG/blob/HEAD/packnet_models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f12377e78b0616c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}