{"id":"W2993553029","doi":"10.48550/arxiv.1812.07032","title":"Boundary loss for highly unbalanced segmentation","year":2018,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Softmax function; Segmentation; Boundary (topology); Cross entropy; Computer science; Computation; Graph; Mathematics; Algorithm; Mathematical optimization; Artificial intelligence; Pattern recognition (psychology); Deep learning; Mathematical analysis; Theoretical computer science","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":[0.0001109966,0.0001366025,0.0001216099,0.00005785532,0.0003418461,0.0001277623,0.0005785692,0.00004847405,0.00001279017],"category_scores_gemma":[0.00002865115,0.000134985,0.00004823432,0.000459219,0.0001213326,0.0005371976,0.0001341093,0.00007468149,0.0002543387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007218305,"about_ca_system_score_gemma":0.00005327414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003149931,"about_ca_topic_score_gemma":0.00002537736,"domain_scores_codex":[0.9988668,0.00002584636,0.0001596996,0.0004420579,0.0001808676,0.0003247241],"domain_scores_gemma":[0.998929,0.0001321775,0.0001181503,0.0005919723,0.0001362621,0.00009247408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002086392,0.000305012,0.001807939,0.00007034881,0.00008459412,0.00001483311,0.004069232,0.001512777,0.165033,0.4756873,0.1203671,0.2308392],"study_design_scores_gemma":[0.002307441,0.0006337148,0.007800289,0.00005202955,0.0000255949,0.00003787777,0.00009164451,0.1023191,0.1387778,0.06885605,0.6781436,0.0009547879],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0236877,0.00006649925,0.9674138,0.006663303,0.0005460164,0.0005305787,0.000008358654,0.0003104951,0.0007732932],"genre_scores_gemma":[0.7035294,0.00002165908,0.2911038,0.001497755,0.0006316633,0.0002589404,0.00001934946,0.00002501239,0.002912422],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6798418,"threshold_uncertainty_score":0.550453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01493113658915044,"score_gpt":0.2889013057592286,"score_spread":0.2739701691700781,"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."}}