{"id":"W2557889580","doi":"10.1109/cvpr.2017.305","title":"Deep Watershed Transform for Instance Segmentation","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":555,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Watershed; Computer science; Artificial intelligence; Conditional random field; Segmentation; Deep learning; Image segmentation; Object (grammar); Convolutional neural network; Matching (statistics); Task (project management); Pattern recognition (psychology); Computer vision; Mathematics; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009903568,0.0000654761,0.00007143688,0.00002325606,0.0002938504,0.0002223566,0.0006291451,0.00002455585,0.000005952425],"category_scores_gemma":[0.00002577493,0.000051591,0.00004083432,0.00002625086,0.00002719514,0.001741103,0.00004291374,0.0000291031,0.000006646053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002114483,"about_ca_system_score_gemma":0.000009561367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007578864,"about_ca_topic_score_gemma":0.00001526632,"domain_scores_codex":[0.9994919,0.000003758146,0.00009851521,0.0001782141,0.00008288363,0.0001447592],"domain_scores_gemma":[0.9994066,0.00001715867,0.00005276249,0.0004358044,0.00005517483,0.00003244864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000130147,0.00001514138,0.00007072755,0.00001354547,0.000004622464,0.000001604318,0.0002356868,0.000002215184,0.006683224,0.03269173,0.0003170322,0.9599515],"study_design_scores_gemma":[0.0004093771,0.0001079287,0.0004791815,0.000006599527,0.000002267212,0.000001865146,0.00001698379,0.01018707,0.9161586,0.06255485,0.009948848,0.0001264553],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002815893,0.00002170051,0.9912105,0.00120377,0.00008019418,0.000302729,6.706375e-7,0.0002004857,0.006698378],"genre_scores_gemma":[0.3522202,0.00004407084,0.6464126,0.0002991408,0.00002665235,0.00004772139,0.000002163483,0.00000490756,0.0009425626],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.959825,"threshold_uncertainty_score":0.2260089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02710488122607905,"score_gpt":0.3232249328594106,"score_spread":0.2961200516333315,"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."}}