{"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/task-agnostic-representation-consolidation-a","title":"Task Agnostic Representation Consolidation: a Self-supervised based Continual Learning Approach","arxiv_id":"2207.06267","date":"2022-07-13","proceeding":null,"authors":["Prashant Bhat","Bahram Zonooz","Elahe Arani"],"abstract":"Continual learning (CL) over non-stationary data streams remains one of the long-standing challenges in deep neural networks (DNNs) as they are prone to catastrophic forgetting. CL models can benefit from self-supervised pre-training as it enables learning more generalizable task-agnostic features. However, the effect of self-supervised pre-training diminishes as the length of task sequences increases. Furthermore, the domain shift between pre-training data distribution and the task distribution reduces the generalizability of the learned representations. To address these limitations, we propose Task Agnostic Representation Consolidation (TARC), a two-stage training paradigm for CL that intertwines task-agnostic and task-specific learning whereby self-supervised training is followed by supervised learning for each task. To further restrict the deviation from the learned representations in the self-supervised stage, we employ a task-agnostic auxiliary loss during the supervised stage. We show that our training paradigm can be easily added to memory- or regularization-based approaches and provides consistent performance gain across more challenging CL settings. We further show that it leads to more robust and well-calibrated models.","url_abs":"https://arxiv.org/abs/2207.06267v1","url_pdf":"https://arxiv.org/pdf/2207.06267v1.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":"task-agnostic-representation-consolidation-a","repo_url":"https://github.com/neurai-lab/tarc","is_official":1,"mentioned_in_paper":1,"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.06267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06267"}},"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/neurai-lab/tarc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":"fac9904f665a5702","entry":"check_integrity","repo":"neurai-lab/tarc","repo_kind":"official","path":"datasets/cifar10_noisy.py","file_url":"https://github.com/neurai-lab/tarc/blob/HEAD/datasets/cifar10_noisy.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac9904f665a5702"}},{"code_sha256_prefix":"915e1c6c38494be9","entry":"list_dir","repo":"neurai-lab/tarc","repo_kind":"official","path":"datasets/cifar10_noisy.py","file_url":"https://github.com/neurai-lab/tarc/blob/HEAD/datasets/cifar10_noisy.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"915e1c6c38494be9"}},{"code_sha256_prefix":"208e196e9582a9a6","entry":"list_files","repo":"neurai-lab/tarc","repo_kind":"official","path":"datasets/cifar10_noisy.py","file_url":"https://github.com/neurai-lab/tarc/blob/HEAD/datasets/cifar10_noisy.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"208e196e9582a9a6"}},{"code_sha256_prefix":"4c2989ace7c5c0da","entry":"conv3x3","repo":"neurai-lab/tarc","repo_kind":"official","path":"backbone/ResNet18.py","file_url":"https://github.com/neurai-lab/tarc/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c2989ace7c5c0da"}},{"code_sha256_prefix":"08b2cc137f0a6c40","entry":"get_resnet18","repo":"neurai-lab/tarc","repo_kind":"official","path":"backbone/ResNet18.py","file_url":"https://github.com/neurai-lab/tarc/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08b2cc137f0a6c40"}},{"code_sha256_prefix":"128b0b445eec8bbc","entry":"resnet18","repo":"neurai-lab/tarc","repo_kind":"official","path":"backbone/ResNet18.py","file_url":"https://github.com/neurai-lab/tarc/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"128b0b445eec8bbc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}