{"id":"W3207216914","doi":"10.48550/arxiv.2110.07376","title":"Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Discriminator; Normalization (sociology); Affine transformation; Computer science; Artificial intelligence; Segmentation; Transformation (genetics); Pattern recognition (psychology); Domain (mathematical analysis); Adaptation (eye); 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":[0.001026315,0.001133484,0.001168859,0.0007778769,0.0005510655,0.0008379259,0.001470604,0.00109417,0.002826954],"category_scores_gemma":[0.00214095,0.0004371517,0.001264221,0.0009762294,0.001293047,0.001889853,0.001771873,0.002165433,0.001509501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007813397,"about_ca_system_score_gemma":0.0009150237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003714696,"about_ca_topic_score_gemma":0.003756579,"domain_scores_codex":[0.999249,0.0001866319,0.00003098772,0.0003276111,0.0001259749,0.00007974247],"domain_scores_gemma":[0.9994044,0.0001914242,0.00005070045,0.0002081394,0.00009908516,0.00004609563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004159422,0.0002436573,0.001655096,0.0001714528,0.0001938569,0.0002361171,0.0002911786,0.3410596,0.05512345,0.03097461,0.008838615,0.5607964],"study_design_scores_gemma":[0.00001216907,0.00004148566,0.0004303605,0.000007412844,0.00002045509,0.00009228334,0.00002361452,0.9726496,0.01060103,0.01364203,0.00246048,0.00001897914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01428761,0.0002898158,0.9818076,0.0001176567,0.00009003473,0.00004285748,0.00008290418,0.001703227,0.001578252],"genre_scores_gemma":[0.5201755,0.0005716425,0.4646555,0.0006114857,0.0002020743,0.0001973474,0.001179148,0.0008943516,0.01151292],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003714696,"threshold_uncertainty_score":0.009457111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05200772985152356,"score_gpt":0.1906380758166798,"score_spread":0.1386303459651562,"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."}}