{"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/ds-al-a-dual-stream-analytic-learning-for","title":"DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning","arxiv_id":"2403.17503","date":"2024-03-26","proceeding":null,"authors":["Huiping Zhuang","Run He","Kai Tong","Ziqian Zeng","Cen Chen","Zhiping Lin"],"abstract":"Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that retain access to past samples. In this paper, to solve the exemplar-free CIL problem, we propose a Dual-Stream Analytic Learning (DS-AL) approach. The DS-AL contains a main stream offering an analytical (i.e., closed-form) linear solution, and a compensation stream improving the inherent under-fitting limitation due to adopting linear mapping. The main stream redefines the CIL problem into a Concatenated Recursive Least Squares (C-RLS) task, allowing an equivalence between the CIL and its joint-learning counterpart. The compensation stream is governed by a Dual-Activation Compensation (DAC) module. This module re-activates the embedding with a different activation function from the main stream one, and seeks fitting compensation by projecting the embedding to the null space of the main stream's linear mapping. Empirical results demonstrate that the DS-AL, despite being an exemplar-free technique, delivers performance comparable with or better than that of replay-based methods across various datasets, including CIFAR-100, ImageNet-100 and ImageNet-Full. Additionally, the C-RLS' equivalent property allows the DS-AL to execute CIL in a phase-invariant manner. This is evidenced by a never-before-seen 500-phase CIL ImageNet task, which performs on a level identical to a 5-phase one. Our codes are available at https://github.com/ZHUANGHP/Analytic-continual-learning.","url_abs":"https://arxiv.org/abs/2403.17503v1","url_pdf":"https://arxiv.org/pdf/2403.17503v1.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":"ds-al-a-dual-stream-analytic-learning-for","repo_url":"https://github.com/ZHUANGHP/Analytic-continual-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"exemplar-free","task_name":"Exemplar-Free"},{"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":{"syntology_url":"https://syntology.ai/paper/2403.17503","atlas_url":"https://app.syntology.ai/?focus=2403.17503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17503"}},"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":"deterministic:regex_extraction","url":"https://github.com/ZHUANGHP/Analytic-continual-learning","reach":null}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"4b43153e61d887ca","entry":"DSAL","repo":"ZHUANGHP/Analytic-continual-learning","repo_kind":"official","path":"analytic/DSAL.py","file_url":"https://github.com/ZHUANGHP/Analytic-continual-learning/blob/HEAD/analytic/DSAL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b43153e61d887ca"}},{"code_sha256_prefix":"47ce601254361537","entry":"RandomBuffer","repo":"ZHUANGHP/Analytic-continual-learning","repo_kind":"official","path":"analytic/DSAL.py","file_url":"https://github.com/ZHUANGHP/Analytic-continual-learning/blob/HEAD/analytic/DSAL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47ce601254361537"}},{"code_sha256_prefix":"4f6df5db2e30fed4","entry":"RecursiveLinear","repo":"ZHUANGHP/Analytic-continual-learning","repo_kind":"official","path":"analytic/DSAL.py","file_url":"https://github.com/ZHUANGHP/Analytic-continual-learning/blob/HEAD/analytic/DSAL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f6df5db2e30fed4"}},{"code_sha256_prefix":"0f139eca807b529f","entry":"AnalyticLinear","repo":"ZHUANGHP/Analytic-continual-learning","repo_kind":"official","path":"analytic/DSAL.py","file_url":"https://github.com/ZHUANGHP/Analytic-continual-learning/blob/HEAD/analytic/DSAL.py","link_basis":"first_harvest_node","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":"0f139eca807b529f"}},{"code_sha256_prefix":"1d08f115abdc4600","entry":"Buffer","repo":"ZHUANGHP/Analytic-continual-learning","repo_kind":"official","path":"analytic/DSAL.py","file_url":"https://github.com/ZHUANGHP/Analytic-continual-learning/blob/HEAD/analytic/DSAL.py","link_basis":"first_harvest_node","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":"1d08f115abdc4600"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}