{"id":"W3215957616","doi":"10.1109/tip.2021.3128311","title":"A Prototypical Knowledge Oriented Adaptation Framework for Semantic Segmentation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Discriminative model; Segmentation; Leverage (statistics); Overfitting; Discriminator; Domain adaptation; Convolutional neural network; Feature learning; Transfer of learning; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002079796,0.000163903,0.0001547145,0.0001498618,0.0005558418,0.0003958142,0.0001812311,0.00009187728,0.00003714123],"category_scores_gemma":[0.00006079323,0.0001747488,0.000100833,0.0008019422,0.00004391346,0.0009329222,0.0000025942,0.000277654,0.00005398771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008362138,"about_ca_system_score_gemma":0.0003020843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001600045,"about_ca_topic_score_gemma":0.000007730359,"domain_scores_codex":[0.9986112,0.000101457,0.0002987848,0.0004761035,0.0002400688,0.0002723527],"domain_scores_gemma":[0.998917,0.0002060899,0.0001141311,0.0002329862,0.0004330682,0.00009667989],"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":[0.00008936698,0.0005359587,0.000003800555,0.0003015324,0.00003296985,0.00001200257,0.00930006,0.005880032,0.01828129,0.005850173,0.00003218903,0.9596806],"study_design_scores_gemma":[0.0009580596,0.0001252772,0.00004197965,0.0002859244,0.00003508024,0.00002866984,0.001331381,0.8929069,0.09837762,0.004447949,0.001165528,0.0002956117],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006082022,0.0001058244,0.9970614,0.0006065391,0.0004525159,0.0005410743,0.000003347692,0.0003064325,0.000314622],"genre_scores_gemma":[0.4182684,0.000006336639,0.580843,0.0001833183,0.00004047879,0.0002883378,0.00000493986,0.00001790083,0.0003472154],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.959385,"threshold_uncertainty_score":0.7126049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03283645738904421,"score_gpt":0.3168077497371934,"score_spread":0.2839712923481492,"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."}}