{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002237843,0.001595057,0.0009439721,0.001151452,0.0007983282,0.00165717,0.001683719,0.002401008,0.005961784],"category_scores_gemma":[0.0071627,0.0005158212,0.0008429046,0.0008265927,0.001193235,0.00249444,0.002558772,0.001994978,0.001783545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001702776,"about_ca_system_score_gemma":0.001137841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003117783,"about_ca_topic_score_gemma":0.004341205,"domain_scores_codex":[0.999164,0.0001376802,0.00006797765,0.0002777494,0.0002371574,0.0001154677],"domain_scores_gemma":[0.9985978,0.000619348,0.0001507245,0.0002521925,0.0002938921,0.00008605207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006978814,0.000201238,0.003541487,0.0002560117,0.00009474009,0.0004153386,0.0001712001,0.6177869,0.02595061,0.02320711,0.02275003,0.3049273],"study_design_scores_gemma":[0.0000168442,0.00004844563,0.0005389908,0.00002643014,0.00001228697,0.0001049756,0.00001953857,0.9795281,0.006638207,0.01098426,0.002071321,0.00001076037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06714731,0.0007274913,0.9192439,0.0008283895,0.0002128388,0.0001369382,0.0006903328,0.003894881,0.00711787],"genre_scores_gemma":[0.6564758,0.0004232896,0.3240429,0.001252621,0.0001734616,0.0003293651,0.003985115,0.00191526,0.01140213],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005961784,"threshold_uncertainty_score":0.01994413,"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."}}