{"id":"W3098535516","doi":"10.1016/j.media.2021.102038","title":"SoftSeg: Advantages of soft versus binary training for image segmentation","year":2021,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund; Canada Research Chairs; Canada Foundation for Innovation; Nvidia","keywords":"Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Voxel; Preprocessor; Binary classification; Image segmentation; Binary number; Ground truth; Pixel; Mathematics; Support vector machine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002028366,0.001010259,0.001296672,0.001192662,0.0004989454,0.00159413,0.001538525,0.002431625,0.003863213],"category_scores_gemma":[0.006337347,0.0005129796,0.0006751518,0.0008191484,0.0009492456,0.002118798,0.002153118,0.001846513,0.001376059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004361795,"about_ca_system_score_gemma":0.0007760197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002222409,"about_ca_topic_score_gemma":0.003095512,"domain_scores_codex":[0.9993176,0.0002055267,0.00003539583,0.0002011904,0.0001757973,0.00006441129],"domain_scores_gemma":[0.9977978,0.001261503,0.00008821941,0.0004175062,0.0003190679,0.0001159509],"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":[0.001050472,0.0003453723,0.001135285,0.0003095148,0.0001543916,0.0001025425,0.000132081,0.1430739,0.05165881,0.01107549,0.004862174,0.7860999],"study_design_scores_gemma":[0.00002031014,0.0001063985,0.0006860216,0.00002336546,0.0000294824,0.0001557727,0.00002541396,0.9640853,0.02334952,0.01022417,0.001276199,0.00001801505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02617947,0.000744801,0.9679716,0.0003253388,0.00007462261,0.00005892594,0.0001435445,0.002943591,0.001558231],"genre_scores_gemma":[0.3406407,0.0007828629,0.6499978,0.0004200923,0.0001910923,0.0001026769,0.0009008525,0.001303635,0.005660386],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003863213,"threshold_uncertainty_score":0.01292372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04295141484576424,"score_gpt":0.3517031474118046,"score_spread":0.3087517325660404,"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."}}