{"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/aetta-label-free-accuracy-estimation-for-test","title":"AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation","arxiv_id":"2404.01351","date":"2024-04-01","proceeding":"CVPR 2024 1","authors":["Taeckyung Lee","Sorn Chottananurak","Taesik Gong","Sung-Ju Lee"],"abstract":"Test-time adaptation (TTA) has emerged as a viable solution to adapt pre-trained models to domain shifts using unlabeled test data. However, TTA faces challenges of adaptation failures due to its reliance on blind adaptation to unknown test samples in dynamic scenarios. Traditional methods for out-of-distribution performance estimation are limited by unrealistic assumptions in the TTA context, such as requiring labeled data or re-training models. To address this issue, we propose AETTA, a label-free accuracy estimation algorithm for TTA. We propose the prediction disagreement as the accuracy estimate, calculated by comparing the target model prediction with dropout inferences. We then improve the prediction disagreement to extend the applicability of AETTA under adaptation failures. Our extensive evaluation with four baselines and six TTA methods demonstrates that AETTA shows an average of 19.8%p more accurate estimation compared with the baselines. We further demonstrate the effectiveness of accuracy estimation with a model recovery case study, showcasing the practicality of our model recovery based on accuracy estimation. The source code is available at https://github.com/taeckyung/AETTA.","url_abs":"https://arxiv.org/abs/2404.01351v1","url_pdf":"https://arxiv.org/pdf/2404.01351v1.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":"aetta-label-free-accuracy-estimation-for-test","repo_url":"https://github.com/taeckyung/aetta","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.01351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01351"}},"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/taeckyung/aetta","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/taeckyung/AETTA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":3,"ran_honours":1,"ran":7,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":12,"ran":12,"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":"fc962c3df9bd26ac","entry":"calc_energy","repo":"taeckyung/AETTA","repo_kind":"official","path":"utils/loss_functions.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/utils/loss_functions.py","link_basis":"plan_row","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":"748df4ce43772fae","entry":"get_avg_online_acc","repo":"taeckyung/AETTA","repo_kind":"official","path":"print_acc.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/print_acc.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"748df4ce43772fae"}},{"code_sha256_prefix":"0764e24b7e85a924","entry":"get_avg_online_acc","repo":"taeckyung/AETTA","repo_kind":"official","path":"print_est.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/print_est.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":"0764e24b7e85a924"}},{"code_sha256_prefix":"7d3f76502e1e286c","entry":"get_dirnames","repo":"taeckyung/AETTA","repo_kind":"official","path":"process_cifar.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/process_cifar.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":"7d3f76502e1e286c"}},{"code_sha256_prefix":"2b4bb33f8c8c082c","entry":"get_normalize_layer","repo":"taeckyung/AETTA","repo_kind":"official","path":"utils/normalize_layer.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/utils/normalize_layer.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":"2b4bb33f8c8c082c"}},{"code_sha256_prefix":"aeeb23c68bb4b797","entry":"get_normalize_std","repo":"taeckyung/AETTA","repo_kind":"official","path":"utils/normalize_layer.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/utils/normalize_layer.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":"aeeb23c68bb4b797"}},{"code_sha256_prefix":"8e952e7f9820216a","entry":"load_data","repo":"taeckyung/AETTA","repo_kind":"official","path":"process_cifar.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/process_cifar.py","link_basis":"plan_row","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":"8e952e7f9820216a"}},{"code_sha256_prefix":"f194bfd61755bba9","entry":"marginal_entropy","repo":"taeckyung/AETTA","repo_kind":"official","path":"utils/loss_functions.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/utils/loss_functions.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":"f194bfd61755bba9"}},{"code_sha256_prefix":"7483be869cdb6276","entry":"process_path","repo":"taeckyung/AETTA","repo_kind":"official","path":"print_acc.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/print_acc.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":"7483be869cdb6276"}},{"code_sha256_prefix":"f170a751d5d3e5aa","entry":"process_path","repo":"taeckyung/AETTA","repo_kind":"official","path":"print_est.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/print_est.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":"f170a751d5d3e5aa"}},{"code_sha256_prefix":"92bc8db96a48bcb0","entry":"reshape","repo":"taeckyung/AETTA","repo_kind":"official","path":"process_cifar.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/process_cifar.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92bc8db96a48bcb0"}},{"code_sha256_prefix":"a9edd84f4eedeec8","entry":"softmax_entropy","repo":"taeckyung/AETTA","repo_kind":"official","path":"utils/loss_functions.py","file_url":"https://github.com/taeckyung/AETTA/blob/HEAD/utils/loss_functions.py","link_basis":"plan_row","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"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}