{"id":"W3137531678","doi":"10.1109/tmi.2021.3067688","title":"Constrained Domain Adaptation for Image Segmentation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Image segmentation; Computer vision; Artificial intelligence; Computer science; Image (mathematics); Adaptation (eye); Scale-space segmentation; Domain adaptation; Segmentation; Domain (mathematical analysis); Pattern recognition (psychology); Mathematics; Physics; Optics","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":[0.0004880549,0.000135279,0.0001427483,0.0001269549,0.0003137334,0.0001982189,0.0002382924,0.00005482866,0.0002869221],"category_scores_gemma":[0.00008007327,0.0001434362,0.0001188257,0.0003630392,0.00009903724,0.0005644526,0.000002460208,0.0002533805,0.0000571715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006720433,"about_ca_system_score_gemma":0.0002960354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006709382,"about_ca_topic_score_gemma":0.00001289147,"domain_scores_codex":[0.9983258,0.0001395167,0.0003075815,0.0003912996,0.0005607607,0.0002750351],"domain_scores_gemma":[0.9989104,0.0003912506,0.00007381997,0.0002311559,0.0001783732,0.0002150118],"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":[0.00002581296,0.0002321015,0.000006842962,0.00003943984,0.00004594199,0.0001492953,0.002862609,0.003848459,0.02619502,0.007793682,0.0003772236,0.9584236],"study_design_scores_gemma":[0.002274785,0.00004132001,0.00004272954,0.00008000511,0.00002029592,0.0001625954,0.002693356,0.9606588,0.02680346,0.003066697,0.003881629,0.000274285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004875577,0.00003640487,0.9893869,0.007595271,0.0008729649,0.0001876111,0.000006977016,0.0002329038,0.001193365],"genre_scores_gemma":[0.4824447,0.00002798252,0.5134721,0.003414583,0.00007992397,0.00009804859,0.00001782471,0.00002033659,0.0004244911],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9581493,"threshold_uncertainty_score":0.5849159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01822661270530067,"score_gpt":0.2846312113572855,"score_spread":0.2664045986519848,"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."}}