{"id":"W4206056756","doi":"10.1007/978-3-030-90439-5_46","title":"Unsupervised Pixel-Wise Weighted Adversarial Domain Adaptation","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Leverage (statistics); Weighting; Pattern recognition (psychology); Domain adaptation; Pixel; Machine learning; Domain (mathematical analysis); Feature (linguistics); Convolutional neural network; Adaptation (eye); Classifier (UML); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001064233,0.0006421858,0.0006325401,0.0009558907,0.0004438841,0.0009665682,0.002706272,0.0004371268,0.0001444398],"category_scores_gemma":[0.0001082897,0.0006440469,0.0002260572,0.001133858,0.000519784,0.0009675155,0.00105921,0.001075008,0.0001315582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000409559,"about_ca_system_score_gemma":0.001241136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002532034,"about_ca_topic_score_gemma":0.00007743253,"domain_scores_codex":[0.9948716,0.0001359516,0.0007232801,0.001935906,0.001548749,0.00078449],"domain_scores_gemma":[0.996912,0.0005466486,0.0003733273,0.001424585,0.000442905,0.0003005035],"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":[0.00002740772,0.00006302385,0.00003204012,0.00005016728,0.00003491103,0.0002608799,0.004953657,0.04733115,0.0008223115,0.1116645,0.00004154397,0.8347183],"study_design_scores_gemma":[0.001032592,0.0001480559,0.0001319927,0.0003722363,0.00001175158,0.00007392278,0.000003910218,0.8669888,0.0003190031,0.1052379,0.0247084,0.0009713584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009952065,0.0004831539,0.9869004,0.001489229,0.002929429,0.0003951618,0.000004393978,0.000280897,0.007417844],"genre_scores_gemma":[0.03555067,0.00008802178,0.9589279,0.00290528,0.0008636139,0.00001442299,0.00004368012,0.00006193945,0.001544495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.833747,"threshold_uncertainty_score":0.9996011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01971505677163591,"score_gpt":0.2344875737945281,"score_spread":0.2147725170228922,"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."}}