{"id":"W2253218192","doi":"10.48550/arxiv.1511.08498","title":"Iterative Instance Segmentation","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; Multidisciplinary University Research Initiative; Nvidia","keywords":"Contiguity; Inference; Computer science; Prior probability; Segmentation; A priori and a posteriori; Sequence (biology); Artificial intelligence; Smoothness; Task (project management); Structured prediction; Algorithm; Pattern recognition (psychology); Machine learning; Bayesian probability; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000102531,0.0002312873,0.0001970488,0.0001206381,0.0001298023,0.00009468703,0.001345965,0.0001361583,0.00000759026],"category_scores_gemma":[0.00001412212,0.0002754111,0.0000777669,0.0006676082,0.00007530087,0.0006427019,0.001323482,0.0003977453,0.0001263844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003412485,"about_ca_system_score_gemma":0.0001534131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001116384,"about_ca_topic_score_gemma":0.00002082102,"domain_scores_codex":[0.9985042,0.00009315582,0.000152332,0.0009302837,0.00008561621,0.0002344773],"domain_scores_gemma":[0.9982577,0.00006432433,0.000248986,0.001041508,0.0002379512,0.0001495256],"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":[0.0000123141,0.00005269213,0.0003166675,0.00001655855,0.00003019845,0.00007277675,0.0004281022,0.5941496,0.00009674273,0.4011639,0.001606301,0.002054214],"study_design_scores_gemma":[0.0003836944,0.00003537403,0.0002033331,0.00004538611,0.00002239423,0.0000036612,0.00005735609,0.6889052,0.0004402498,0.3072876,0.002168778,0.0004469607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04565345,0.00007485611,0.9492133,0.0001751559,0.0003365498,0.0003867557,0.00001504635,0.0003078704,0.003837035],"genre_scores_gemma":[0.9782147,0.0001080678,0.01979537,0.000175922,0.00007559482,0.000004961781,0.00003338257,0.00001325099,0.001578702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9325613,"threshold_uncertainty_score":0.9999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09684413545597585,"score_gpt":0.2224549496881535,"score_spread":0.1256108142321777,"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."}}