{"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/a-model-or-603-exemplars-towards-memory","title":"A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning","arxiv_id":"2205.13218","date":"2022-05-26","proceeding":null,"authors":["Da-Wei Zhou","Qi-Wei Wang","Han-Jia Ye","De-Chuan Zhan"],"abstract":"Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical CIL methods tend to save representative exemplars from former classes to resist forgetting, while recent works find that storing models from history can substantially boost the performance. However, the stored models are not counted into the memory budget, which implicitly results in unfair comparisons. We find that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work, especially for the case with limited memory budgets. As a result, we need to holistically evaluate different CIL methods at different memory scales and simultaneously consider accuracy and memory size for measurement. On the other hand, we dive deeply into the construction of the memory buffer for memory efficiency. By analyzing the effect of different layers in the network, we find that shallow and deep layers have different characteristics in CIL. Motivated by this, we propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel. MEMO extends specialized layers based on the shared generalized representations, efficiently extracting diverse representations with modest cost and maintaining representative exemplars. Extensive experiments on benchmark datasets validate MEMO's competitive performance. Code is available at: https://github.com/wangkiw/ICLR23-MEMO","url_abs":"https://arxiv.org/abs/2205.13218v2","url_pdf":"https://arxiv.org/pdf/2205.13218v2.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":"a-model-or-603-exemplars-towards-memory","repo_url":"https://github.com/wangkiw/iclr23-memo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-model-or-603-exemplars-towards-memory","repo_url":"https://github.com/zhoudw-zdw/cil_survey","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.13218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13218"}},"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":"deterministic:regex_extraction","url":"https://github.com/wangkiw/ICLR23-MEMO","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhoudw-zdw/cil_survey","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangkiw/iclr23-memo","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":1,"ran_honours":2,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"a0ee070a256009b9","entry":"AdaptiveNet","repo":"wangkiw/iclr23-memo","repo_kind":"official","path":"models/memo.py","file_url":"https://github.com/wangkiw/iclr23-memo/blob/HEAD/models/memo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a0ee070a256009b9"}},{"code_sha256_prefix":"718d523922efedea","entry":"SimpleLinear","repo":"wangkiw/iclr23-memo","repo_kind":"official","path":"models/memo.py","file_url":"https://github.com/wangkiw/iclr23-memo/blob/HEAD/models/memo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"718d523922efedea"}},{"code_sha256_prefix":"fa5bbac75c929c9f","entry":"accuracy","repo":"wangkiw/iclr23-memo","repo_kind":"official","path":"models/memo.py","file_url":"https://github.com/wangkiw/iclr23-memo/blob/HEAD/models/memo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fa5bbac75c929c9f"}},{"code_sha256_prefix":"6bdbe3d6368c4cde","entry":"count_parameters","repo":"wangkiw/iclr23-memo","repo_kind":"official","path":"models/memo.py","file_url":"https://github.com/wangkiw/iclr23-memo/blob/HEAD/models/memo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6bdbe3d6368c4cde"}},{"code_sha256_prefix":"929c76a2fa2e8c42","entry":"tensor2numpy","repo":"wangkiw/iclr23-memo","repo_kind":"official","path":"models/memo.py","file_url":"https://github.com/wangkiw/iclr23-memo/blob/HEAD/models/memo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"929c76a2fa2e8c42"}},{"code_sha256_prefix":"eae1b41c41d8cbe3","entry":"BaseLearner","repo":"wangkiw/iclr23-memo","repo_kind":"official","path":"models/memo.py","file_url":"https://github.com/wangkiw/iclr23-memo/blob/HEAD/models/memo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eae1b41c41d8cbe3"}},{"code_sha256_prefix":"dcb9c9ddfc76203a","entry":"MEMO","repo":"wangkiw/iclr23-memo","repo_kind":"official","path":"models/memo.py","file_url":"https://github.com/wangkiw/iclr23-memo/blob/HEAD/models/memo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcb9c9ddfc76203a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}