{"id":"W4402916274","doi":"10.1109/cvprw63382.2024.00271","title":"MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Prior probability; Segmentation; Domain adaptation; Artificial intelligence; Motion (physics); Adaptation (eye); Domain (mathematical analysis); Computer vision; Bayesian probability; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008770532,0.0009762094,0.0007503565,0.001178586,0.0004537195,0.0007286553,0.001246759,0.000882672,0.001494312],"category_scores_gemma":[0.001959834,0.0003935011,0.000819276,0.0008690166,0.0007791014,0.001651835,0.001609741,0.001265099,0.0008261588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004938375,"about_ca_system_score_gemma":0.00101215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003683479,"about_ca_topic_score_gemma":0.005304959,"domain_scores_codex":[0.9995458,0.0001048512,0.00001774703,0.0001909928,0.00008142119,0.00005920186],"domain_scores_gemma":[0.9994386,0.0002051585,0.00006176923,0.0001447595,0.00009906777,0.00005061899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003377904,0.0002939516,0.002236712,0.0002412892,0.0001269061,0.0001821923,0.0003377173,0.2087353,0.09262685,0.01515364,0.00725529,0.6724724],"study_design_scores_gemma":[0.00001093369,0.00005482712,0.0006253303,0.00001167586,0.00001276983,0.00006667985,0.00004131896,0.9761102,0.01239316,0.007576729,0.003081914,0.00001445852],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01824487,0.000315564,0.9781154,0.0001011856,0.00004468884,0.00006265025,0.0001273077,0.001724269,0.001264103],"genre_scores_gemma":[0.3317161,0.0004862843,0.6618032,0.0003478358,0.000101381,0.0002098868,0.001391997,0.0005411186,0.003402098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003683479,"threshold_uncertainty_score":0.0073241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02416780784396748,"score_gpt":0.264768606561578,"score_spread":0.2406007987176105,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}