{"id":"W4288375829","doi":"","title":"On Direct Distribution Matching for Adapting Segmentation Networks","year":2020,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Segmentation; Discriminator; Computer science; Artificial intelligence; Matching (statistics); Adversarial system; Context (archaeology); Stability (learning theory); Pattern recognition (psychology); Kernel (algebra); Scale-space segmentation; Image segmentation; Minification; Computer vision; Machine learning; Mathematics; Geography","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004661507,0.0003744249,0.0003820336,0.0001180843,0.0006951715,0.001095203,0.00150651,0.0002506254,0.0000228559],"category_scores_gemma":[0.001704921,0.0004224969,0.000267978,0.0004246778,0.00007477178,0.0002964697,0.001106831,0.0007494488,0.00002800352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002189998,"about_ca_system_score_gemma":0.0001821025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001554885,"about_ca_topic_score_gemma":0.0000895412,"domain_scores_codex":[0.9941798,0.003223312,0.0005948426,0.001085118,0.0004920657,0.0004248466],"domain_scores_gemma":[0.9938573,0.002858911,0.0007441308,0.001313221,0.001007903,0.0002185113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003736922,0.0002782572,0.0001040425,0.0001877506,0.000107422,0.00000556741,0.01064545,0.04165669,0.001094651,0.7522091,0.002502617,0.1911711],"study_design_scores_gemma":[0.000646261,0.000001632067,0.0005972114,0.001112332,0.00003077411,0.000003066991,0.0001285735,0.9653712,0.0043642,0.02064491,0.006566556,0.0005333162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002697073,0.000233884,0.9740583,0.009336769,0.0004829917,0.0007199834,0.00005430556,0.0006096723,0.01180706],"genre_scores_gemma":[0.7696682,0.0001130402,0.2266492,0.0004207872,0.00006629102,0.0001851846,0.001636291,0.00004932066,0.001211665],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9237145,"threshold_uncertainty_score":0.9999418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02183591015221473,"score_gpt":0.246523171576899,"score_spread":0.2246872614246842,"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."}}