{"id":"W3043064029","doi":"10.1109/wacv48630.2021.00138","title":"Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genetec (Canada); École de Technologie Supérieure","funders":"","keywords":"Domain (mathematical analysis); Computer science; Adaptation (eye); Artificial intelligence; Domain adaptation; Process (computing); Domain knowledge; Machine learning; Labeled data; Pattern recognition (psychology); Mathematics; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000487288,0.0004094807,0.0004239076,0.0001537574,0.0002439844,0.000850013,0.0009440358,0.0003508483,0.0002385271],"category_scores_gemma":[0.0001386426,0.0004147546,0.0002437376,0.0004901403,0.00005482475,0.0007089628,0.001180398,0.0006399344,0.0002043658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001743959,"about_ca_system_score_gemma":0.0004711123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001219765,"about_ca_topic_score_gemma":0.0001071157,"domain_scores_codex":[0.9970286,0.0004377129,0.0005980583,0.001102357,0.0004486127,0.000384589],"domain_scores_gemma":[0.9979886,0.0001727023,0.000286693,0.001019308,0.0003920403,0.0001406141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005374812,0.001515507,0.002511848,0.0009285043,0.0005122532,0.0001639304,0.262808,0.3290046,0.002068864,0.257185,0.001724709,0.1415231],"study_design_scores_gemma":[0.0007968577,0.00002388621,0.006706159,0.0001273687,0.00001281647,0.000006516938,0.002493708,0.9672182,0.0002815905,0.007503398,0.01421289,0.0006166198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005001571,0.0009736929,0.9672836,0.0006086176,0.001648986,0.000427182,0.000004342661,0.0006269788,0.023425],"genre_scores_gemma":[0.396699,0.00006043826,0.6009791,0.0002116424,0.0001138891,0.00004680427,0.0002191737,0.00002563188,0.001644348],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6382136,"threshold_uncertainty_score":0.9998304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07176694587146469,"score_gpt":0.3045953406013121,"score_spread":0.2328283947298474,"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."}}