{"url":"/task/test-time-adaptation","name":"Test-time Adaptation","slug":"test-time-adaptation","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":484,"papers_with_code":229,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/test-time-adaptation-on-imagenet-c","slug":"test-time-adaptation-on-imagenet-c","dataset":"ImageNet-C","dataset_url":"/dataset/imagenet-c","rows_in_archive":1,"metrics":["Mean Accuracy"],"first_row_in_archive_order":{"model":"DeYO","paper_title":"Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors","paper_url":"/paper/entropy-is-not-enough-for-test-time","paper_date":"2024-03-12","arxiv_id":"2403.07366","code_links":[{"title":"Jhyun17/DeYO","url":"https://github.com/Jhyun17/DeYO"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":1}}}],"datasets":[{"url":"/dataset/imagenet-c","name":"ImageNet-C","full_name":"ImageNet-C","num_papers_in_archive":602},{"url":"/dataset/dade","name":"DADE","full_name":"Driving Agents in Dynamic Environments","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/domain-adaptation","name":"Domain Adaptation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":229,"tagged_in_all":484,"items":[{"url":"/paper/benchmarking-robustness-of-3d-point-cloud","title":"Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions","date":"2022-01-28","arxiv_id":"2201.12296","repositories_listed":6,"syntology":{"n":29,"n_ran":14,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/advances-in-multimodal-adaptation-and","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","date":"2025-01-30","arxiv_id":"2501.18592","repositories_listed":5,"syntology":null},{"url":"/paper/continual-test-time-domain-adaptation","title":"Continual Test-Time Domain Adaptation","date":"2022-03-25","arxiv_id":"2203.13591","repositories_listed":3,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":4}},{"url":"/paper/controllable-continual-test-time-adaptation","title":"Controllable Continual Test-Time Adaptation","date":"2024-05-23","arxiv_id":"2405.14602","repositories_listed":2,"syntology":null},{"url":"/paper/multi-stream-cellular-test-time-adaptation-of","title":"Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments","date":"2024-04-27","arxiv_id":"2404.17930","repositories_listed":2,"syntology":null},{"url":"/paper/test-time-adaptation-for-blind-image-quality","title":"Test Time Adaptation for Blind Image Quality Assessment","date":"2023-07-27","arxiv_id":"2307.14735","repositories_listed":2,"syntology":null},{"url":"/paper/vida-homeostatic-visual-domain-adapter-for","title":"ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation","date":"2023-06-07","arxiv_id":"2306.04344","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/adanpc-exploring-non-parametric-classifier","title":"AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation","date":"2023-04-25","arxiv_id":"2304.12566","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/mecta-memory-economic-continual-test-time","title":"MECTA: Memory-Economic Continual Test-Time Model Adaptation","date":"2023-02-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/test-time-adaptation-via-self-training-with","title":"Test-Time Adaptation via Self-Training with Nearest Neighbor Information","date":"2022-07-08","arxiv_id":"2207.10792","repositories_listed":2,"syntology":{"n":19,"n_ran":13,"n_unverified":6,"n_pointer_only":19}},{"url":"/paper/listen-adapt-better-wer-source-free-single","title":"Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition","date":"2022-03-27","arxiv_id":"2203.14222","repositories_listed":2,"syntology":null},{"url":"/paper/auxadapt-stable-and-efficient-test-time","title":"AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation","date":"2021-10-24","arxiv_id":"2110.12369","repositories_listed":2,"syntology":null},{"url":"/paper/memo-test-time-robustness-via-adaptation-and","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","date":"2021-10-18","arxiv_id":"2110.09506","repositories_listed":2,"syntology":{"n":18,"n_ran":14,"n_unverified":4,"n_pointer_only":15}},{"url":"/paper/fully-test-time-adaptation-by-entropy","title":"Tent: Fully Test-time Adaptation by Entropy Minimization","date":"2020-06-18","arxiv_id":"2006.10726","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/test-time-adaptable-neural-networks-for","title":"Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation","date":"2020-04-09","arxiv_id":"2004.04668","repositories_listed":2,"syntology":null},{"url":"/paper/stepwise-decomposition-and-dual-stream-focus","title":"Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation","date":"2025-06-07","arxiv_id":"2506.06818","repositories_listed":1,"syntology":null},{"url":"/paper/texttt-avrobustbench-benchmarking-the","title":"$\\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time","date":"2025-05-31","arxiv_id":"2506.00358","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/test-time-adaptation-of-vision-language","title":"Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation","date":"2025-05-28","arxiv_id":"2505.21844","repositories_listed":1,"syntology":null},{"url":"/paper/think-twice-before-adaptation-improving","title":"Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation","date":"2025-05-24","arxiv_id":"2505.18787","repositories_listed":1,"syntology":null},{"url":"/paper/test-time-adaptation-with-binary-feedback","title":"Test-Time Adaptation with Binary Feedback","date":"2025-05-24","arxiv_id":"2505.18514","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/ranked-entropy-minimization-for-continual","title":"Ranked Entropy Minimization for Continual Test-Time Adaptation","date":"2025-05-22","arxiv_id":"2505.16441","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/uniformity-first-uniformity-aware-test-time","title":"Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption","date":"2025-05-19","arxiv_id":"2505.12912","repositories_listed":1,"syntology":null},{"url":"/paper/from-local-details-to-global-context","title":"From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection","date":"2025-05-19","arxiv_id":"2505.13233","repositories_listed":1,"syntology":null},{"url":"/paper/apcotta-continual-test-time-adaptation-for","title":"APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds","date":"2025-05-15","arxiv_id":"2505.09971","repositories_listed":1,"syntology":null},{"url":"/paper/threshold-modulation-for-online-test-time","title":"Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks","date":"2025-05-08","arxiv_id":"2505.05375","repositories_listed":1,"syntology":null},{"url":"/paper/teda-boosting-vision-lanuage-models-for-zero","title":"TeDA: Boosting Vision-Lanuage Models for Zero-Shot 3D Object Retrieval via Testing-time Distribution Alignment","date":"2025-05-05","arxiv_id":"2505.02325","repositories_listed":1,"syntology":null},{"url":"/paper/cosmic-clique-oriented-semantic-multi-space","title":"COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation","date":"2025-03-30","arxiv_id":"2503.23388","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/surgeon-memory-adaptive-fully-test-time","title":"SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity","date":"2025-03-26","arxiv_id":"2503.20354","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_unverified":4,"n_pointer_only":19}},{"url":"/paper/test-time-domain-generalization-via-universe","title":"Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation","date":"2025-03-17","arxiv_id":"2503.13012","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/scap-transductive-test-time-adaptation-via-1","title":"SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting","date":"2025-03-17","arxiv_id":"2503.12866","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}