{"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/c-sfda-a-curriculum-learning-aided-self","title":"C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation","arxiv_id":"2303.17132","date":"2023-03-30","proceeding":"CVPR 2023 1","authors":["Nazmul Karim","Niluthpol Chowdhury Mithun","Abhinav Rajvanshi","Han-Pang Chiu","Supun Samarasekera","Nazanin Rahnavard"],"abstract":"Unsupervised domain adaptation (UDA) approaches focus on adapting models trained on a labeled source domain to an unlabeled target domain. UDA methods have a strong assumption that the source data is accessible during adaptation, which may not be feasible in many real-world scenarios due to privacy concerns and resource constraints of devices. In this regard, source-free domain adaptation (SFDA) excels as access to source data is no longer required during adaptation. Recent state-of-the-art (SOTA) methods on SFDA mostly focus on pseudo-label refinement based self-training which generally suffers from two issues: i) inevitable occurrence of noisy pseudo-labels that could lead to early training time memorization, ii) refinement process requires maintaining a memory bank which creates a significant burden in resource constraint scenarios. To address these concerns, we propose C-SFDA, a curriculum learning aided self-training framework for SFDA that adapts efficiently and reliably to changes across domains based on selective pseudo-labeling. Specifically, we employ a curriculum learning scheme to promote learning from a restricted amount of pseudo labels selected based on their reliabilities. This simple yet effective step successfully prevents label noise propagation during different stages of adaptation and eliminates the need for costly memory-bank based label refinement. Our extensive experimental evaluations on both image recognition and semantic segmentation tasks confirm the effectiveness of our method. C-SFDA is readily applicable to online test-time domain adaptation and also outperforms previous SOTA methods in this task.","url_abs":"https://arxiv.org/abs/2303.17132v1","url_pdf":"https://arxiv.org/pdf/2303.17132v1.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":"c-sfda-a-curriculum-learning-aided-self","repo_url":"https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"source-free-domain-adaptation","task_name":"Source-Free Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/source-free-domain-adaptation-on-visda-2017","task":"Source-Free Domain Adaptation","dataset":"VisDA-2017","model":"C-SFDA","rank_in_archive_order":5,"of":10,"metrics":{"Accuracy":"87.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.17132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17132"}},"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/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation","reach":null}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"1d0329a2deb6eac4","entry":"cross_entropy_loss","repo":"nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation","repo_kind":"official","path":"target_csfda.py","file_url":"https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation/blob/HEAD/target_csfda.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":"1d0329a2deb6eac4"}},{"code_sha256_prefix":"30d177c0d61ab20d","entry":"propagation_loss","repo":"nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation","repo_kind":"official","path":"target_csfda.py","file_url":"https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation/blob/HEAD/target_csfda.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":"30d177c0d61ab20d"}},{"code_sha256_prefix":"8f6d0dd0f7edbb34","entry":"classification_loss","repo":"nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation","repo_kind":"official","path":"target_csfda.py","file_url":"https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation/blob/HEAD/target_csfda.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":"8f6d0dd0f7edbb34"}},{"code_sha256_prefix":"dc6d5d3f0fab700c","entry":"eval_and_label_dataset","repo":"nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation","repo_kind":"official","path":"target_csfda.py","file_url":"https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation/blob/HEAD/target_csfda.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":"dc6d5d3f0fab700c"}},{"code_sha256_prefix":"7ea43055a34181cd","entry":"train_csfda","repo":"nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation","repo_kind":"official","path":"target_csfda.py","file_url":"https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation/blob/HEAD/target_csfda.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":"7ea43055a34181cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}