{"id":"W2560311620","doi":"10.1007/978-3-319-50835-1_22","title":"Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":903,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Softmax function; Artificial intelligence; Computer science; Segmentation; Intersection (aeronautics); Pattern recognition (psychology); Object (grammar); Image segmentation; Artificial neural network; Deep learning; Object detection; Deep neural networks; Pixel; Computer vision; Cartography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.003636495,0.002572824,0.00554741,0.002103725,0.00135242,0.003967183,0.005821585,0.005882898,0.009774853],"category_scores_gemma":[0.009873355,0.002768974,0.002586849,0.00298978,0.002731928,0.005506352,0.005767575,0.00515059,0.002299388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00413044,"about_ca_system_score_gemma":0.003998208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01522033,"about_ca_topic_score_gemma":0.02012968,"domain_scores_codex":[0.9979552,0.0004593595,0.0001497958,0.0006708223,0.0004247504,0.0003401349],"domain_scores_gemma":[0.9958494,0.002658432,0.0002712428,0.0004185546,0.0005562395,0.0002461204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008549137,0.0002934176,0.001061033,0.0002977085,0.0001866434,0.0001042508,0.0002352765,0.6217884,0.004671418,0.02297044,0.009231383,0.3383052],"study_design_scores_gemma":[0.00001222076,0.00003054128,0.00004889697,0.00001520514,0.00001211662,0.0000142048,0.00001512328,0.9913588,0.001120322,0.007005331,0.0003603165,0.000006973479],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02859366,0.001388516,0.9622418,0.0005272529,0.0001258286,0.00008603026,0.0002527439,0.003932157,0.002852027],"genre_scores_gemma":[0.3436434,0.000710809,0.6396294,0.0005914337,0.0002722763,0.0003078418,0.00206968,0.002507783,0.01026743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01522033,"threshold_uncertainty_score":0.03270018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01384282197705767,"score_gpt":0.2666441925100097,"score_spread":0.252801370532952,"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."}}