{"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/sotta-robust-test-time-adaptation-on-noisy-1","title":"SoTTA: Robust Test-Time Adaptation on Noisy Data Streams","arxiv_id":"2310.10074","date":"2023-10-16","proceeding":"NeurIPS 2023 11","authors":["Taesik Gong","Yewon Kim","Taeckyung Lee","Sorn Chottananurak","Sung-Ju Lee"],"abstract":"Test-time adaptation (TTA) aims to address distributional shifts between training and testing data using only unlabeled test data streams for continual model adaptation. However, most TTA methods assume benign test streams, while test samples could be unexpectedly diverse in the wild. For instance, an unseen object or noise could appear in autonomous driving. This leads to a new threat to existing TTA algorithms; we found that prior TTA algorithms suffer from those noisy test samples as they blindly adapt to incoming samples. To address this problem, we present Screening-out Test-Time Adaptation (SoTTA), a novel TTA algorithm that is robust to noisy samples. The key enabler of SoTTA is two-fold: (i) input-wise robustness via high-confidence uniform-class sampling that effectively filters out the impact of noisy samples and (ii) parameter-wise robustness via entropy-sharpness minimization that improves the robustness of model parameters against large gradients from noisy samples. Our evaluation with standard TTA benchmarks with various noisy scenarios shows that our method outperforms state-of-the-art TTA methods under the presence of noisy samples and achieves comparable accuracy to those methods without noisy samples. The source code is available at https://github.com/taeckyung/SoTTA .","url_abs":"https://arxiv.org/abs/2310.10074v1","url_pdf":"https://arxiv.org/pdf/2310.10074v1.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":"sotta-robust-test-time-adaptation-on-noisy-1","repo_url":"https://github.com/taeckyung/SoTTA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.10074","atlas_url":"https://app.syntology.ai/?focus=2310.10074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10074"}},"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/taeckyung/SoTTA","reach":null}],"summary":{"ran":5,"ran_fixture":2,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":13,"ran":8,"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":"37954f9b076ab80e","entry":"CSTU","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"37954f9b076ab80e"}},{"code_sha256_prefix":"e8b803dc0956626a","entry":"ConfFIFO","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"e8b803dc0956626a"}},{"code_sha256_prefix":"e2796dd5351a82a0","entry":"FIFO","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"e2796dd5351a82a0"}},{"code_sha256_prefix":"cb6c1ea449710403","entry":"HLoss","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb6c1ea449710403"}},{"code_sha256_prefix":"a829fc46b04e2042","entry":"MemoryItem","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"a829fc46b04e2042"}},{"code_sha256_prefix":"fc962c3df9bd26ac","entry":"calc_energy","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc962c3df9bd26ac"}},{"code_sha256_prefix":"bde04657eba9f1f5","entry":"sam_collect_params","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bde04657eba9f1f5"}},{"code_sha256_prefix":"a9edd84f4eedeec8","entry":"softmax_entropy","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9edd84f4eedeec8"}},{"code_sha256_prefix":"d2cf21a1fafc8cca","entry":"DNN","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"d2cf21a1fafc8cca"}},{"code_sha256_prefix":"7c10fe54b79944cb","entry":"HUS","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"7c10fe54b79944cb"}},{"code_sha256_prefix":"d02457bfc418d32b","entry":"SoTTA","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"d02457bfc418d32b"}},{"code_sha256_prefix":"59771617b119cc63","entry":"load_cache","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"59771617b119cc63"}},{"code_sha256_prefix":"88a3a9b822c1f39f","entry":"save_cache","repo":"taeckyung/SoTTA","repo_kind":"official","path":"learner/sotta.py","file_url":"https://github.com/taeckyung/SoTTA/blob/HEAD/learner/sotta.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":"88a3a9b822c1f39f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}