{"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/adapt-your-teacher-improving-knowledge","title":"Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning","arxiv_id":"2308.09544","date":"2023-08-18","proceeding":null,"authors":["Filip Szatkowski","Mateusz Pyla","Marcin Przewięźlikowski","Sebastian Cygert","Bartłomiej Twardowski","Tomasz Trzciński"],"abstract":"In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KD-based methods are successfully used in CIL, but they often struggle to regularize the model without access to exemplars of the training data from previous tasks. Our analysis reveals that this issue originates from substantial representation shifts in the teacher network when dealing with out-of-distribution data. This causes large errors in the KD loss component, leading to performance degradation in CIL models. Inspired by recent test-time adaptation methods, we introduce Teacher Adaptation (TA), a method that concurrently updates the teacher and the main models during incremental training. Our method seamlessly integrates with KD-based CIL approaches and allows for consistent enhancement of their performance across multiple exemplar-free CIL benchmarks. The source code for our method is available at https://github.com/fszatkowski/cl-teacher-adaptation.","url_abs":"https://arxiv.org/abs/2308.09544v3","url_pdf":"https://arxiv.org/pdf/2308.09544v3.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":"adapt-your-teacher-improving-knowledge","repo_url":"https://github.com/fszatkowski/cl-teacher-adaptation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.09544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09544"}},"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/fszatkowski/cl-teacher-adaptation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"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":"7700b49fd962f8dd","entry":"cka","repo":"fszatkowski/cl-teacher-adaptation","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/fszatkowski/cl-teacher-adaptation/blob/HEAD/src/metrics.py","link_basis":"first_harvest_node","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":"7700b49fd962f8dd"}},{"code_sha256_prefix":"0ea0fa75daf13d1f","entry":"cm","repo":"fszatkowski/cl-teacher-adaptation","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/fszatkowski/cl-teacher-adaptation/blob/HEAD/src/metrics.py","link_basis":"first_harvest_node","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":"0ea0fa75daf13d1f"}},{"code_sha256_prefix":"2e179edce79cd470","entry":"last_layer_analysis","repo":"fszatkowski/cl-teacher-adaptation","repo_kind":"official","path":"src/last_layer_analysis.py","file_url":"https://github.com/fszatkowski/cl-teacher-adaptation/blob/HEAD/src/last_layer_analysis.py","link_basis":"plan_row","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":"2e179edce79cd470"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}