{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003119507,0.0005777522,0.000771452,0.0008235513,0.0002655737,0.00109918,0.001075132,0.001137187,0.005110562],"category_scores_gemma":[0.00118203,0.0003210764,0.0006641019,0.001225445,0.0006423885,0.001660209,0.001009894,0.001621077,0.001723497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007637361,"about_ca_system_score_gemma":0.0006893747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002482198,"about_ca_topic_score_gemma":0.003820059,"domain_scores_codex":[0.9998049,0.00002213526,0.000007745252,0.00006400246,0.00007273268,0.0000285325],"domain_scores_gemma":[0.9998513,0.00005396015,0.00001697067,0.00003622053,0.00002845336,0.00001309546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001451138,0.00007002657,0.0007572224,0.0001962562,0.00006887822,0.0002430503,0.00008981358,0.2921299,0.04500487,0.1092491,0.01416406,0.5378817],"study_design_scores_gemma":[0.000007789318,0.00001670738,0.0002130477,0.000009277884,0.00001028413,0.0001156555,0.0000111266,0.9336739,0.01411072,0.04448371,0.007336496,0.00001125981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006352257,0.00036193,0.9885836,0.0002644275,0.00004106242,0.00003287457,0.0002175963,0.00190605,0.002240215],"genre_scores_gemma":[0.2900169,0.001173936,0.6956959,0.0002923691,0.0001312284,0.0001293879,0.001926106,0.001023403,0.009610687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005110562,"threshold_uncertainty_score":0.01709652,"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."}}