{"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/saliency-guided-hidden-associative-replay-for","title":"Saliency-Guided Hidden Associative Replay for Continual Learning","arxiv_id":"2310.04334","date":"2023-10-06","proceeding":null,"authors":["Guangji Bai","Qilong Zhao","Xiaoyang Jiang","Yifei Zhang","Liang Zhao"],"abstract":"Continual Learning is a burgeoning domain in next-generation AI, focusing on training neural networks over a sequence of tasks akin to human learning. While CL provides an edge over traditional supervised learning, its central challenge remains to counteract catastrophic forgetting and ensure the retention of prior tasks during subsequent learning. Amongst various strategies to tackle this, replay based methods have emerged as preeminent, echoing biological memory mechanisms. However, these methods are memory intensive, often preserving entire data samples, an approach inconsistent with humans selective memory retention of salient experiences. While some recent works have explored the storage of only significant portions of data in episodic memory, the inherent nature of partial data necessitates innovative retrieval mechanisms. Current solutions, like inpainting, approximate full data reconstruction from partial cues, a method that diverges from genuine human memory processes. Addressing these nuances, this paper presents the Saliency Guided Hidden Associative Replay for Continual Learning. This novel framework synergizes associative memory with replay-based strategies. SHARC primarily archives salient data segments via sparse memory encoding. Importantly, by harnessing associative memory paradigms, it introduces a content focused memory retrieval mechanism, promising swift and near-perfect recall, bringing CL a step closer to authentic human memory processes. Extensive experimental results demonstrate the effectiveness of our proposed method for various continual learning tasks.","url_abs":"https://arxiv.org/abs/2310.04334v1","url_pdf":"https://arxiv.org/pdf/2310.04334v1.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":"saliency-guided-hidden-associative-replay-for","repo_url":"https://github.com/baithebest/sharc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.04334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04334"}},"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/baithebest/sharc","reach":{"status":"ok"}}],"summary":{"ran":5,"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":"e3d484150b4f907c","entry":"modified_kl_div","repo":"baithebest/sharc","repo_kind":"official","path":"models/lwf.py","file_url":"https://github.com/baithebest/sharc/blob/HEAD/models/lwf.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":"e3d484150b4f907c"}},{"code_sha256_prefix":"5d65b508e8b1cbad","entry":"project","repo":"baithebest/sharc","repo_kind":"official","path":"models/agem_bpcn.py","file_url":"https://github.com/baithebest/sharc/blob/HEAD/models/agem_bpcn.py","link_basis":"harvester_set","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":"5d65b508e8b1cbad"}},{"code_sha256_prefix":"fe96388bfd0c1cdf","entry":"sample_from_memory","repo":"baithebest/sharc","repo_kind":"official","path":"models/agem_bpcn.py","file_url":"https://github.com/baithebest/sharc/blob/HEAD/models/agem_bpcn.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":"fe96388bfd0c1cdf"}},{"code_sha256_prefix":"4a877d95a44922ce","entry":"sample_from_memory2","repo":"baithebest/sharc","repo_kind":"official","path":"models/derpp_bpcn.py","file_url":"https://github.com/baithebest/sharc/blob/HEAD/models/derpp_bpcn.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":"4a877d95a44922ce"}},{"code_sha256_prefix":"bc5d184387cac930","entry":"smooth","repo":"baithebest/sharc","repo_kind":"official","path":"models/lwf.py","file_url":"https://github.com/baithebest/sharc/blob/HEAD/models/lwf.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":"bc5d184387cac930"}},{"code_sha256_prefix":"4c2989ace7c5c0da","entry":"conv3x3","repo":"baithebest/sharc","repo_kind":"official","path":"backbone/ResNet18.py","file_url":"https://github.com/baithebest/sharc/blob/HEAD/backbone/ResNet18.py","link_basis":"harvester_set","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":"4c2989ace7c5c0da"}},{"code_sha256_prefix":"7761260a69a3f1be","entry":"resnet18","repo":"baithebest/sharc","repo_kind":"official","path":"backbone/ResNet18.py","file_url":"https://github.com/baithebest/sharc/blob/HEAD/backbone/ResNet18.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":"7761260a69a3f1be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}