{"id":"W2060223645","doi":"10.1007/s11263-009-0251-z","title":"Benchmarking Image Segmentation Algorithms","year":2009,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Benchmarking; Segmentation; Image segmentation; Segmentation-based object categorization; Scale-space segmentation; Artificial intelligence; Benchmark (surveying); Computer science; Ground truth; Pattern recognition (psychology); Precision and recall; Minimum spanning tree-based segmentation; Complement (music); Algorithm; Computer vision","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":[0.004514224,0.002193089,0.001844894,0.004298625,0.001346862,0.00296226,0.003436335,0.003713415,0.01347659],"category_scores_gemma":[0.01545518,0.0008261253,0.001323916,0.004456138,0.0008498799,0.00253742,0.001856268,0.00104948,0.004689417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002253751,"about_ca_system_score_gemma":0.002093497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007999467,"about_ca_topic_score_gemma":0.008672968,"domain_scores_codex":[0.9938774,0.001497994,0.0005313298,0.001442093,0.002068985,0.000582238],"domain_scores_gemma":[0.9912676,0.002829468,0.0003142676,0.002143958,0.003185441,0.0002592833],"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":[0.002762024,0.00117638,0.004970122,0.001157276,0.0007253017,0.0003097886,0.0001825274,0.2858536,0.04216892,0.009550286,0.03531423,0.6158295],"study_design_scores_gemma":[0.0002362135,0.0006930371,0.004333047,0.00006655817,0.0001516963,0.0003359513,0.000153693,0.9135994,0.0638958,0.005675129,0.0108084,0.00005102997],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.476306,0.008033436,0.4246272,0.001496571,0.001904777,0.001027306,0.006881395,0.03728865,0.04243468],"genre_scores_gemma":[0.604163,0.001055455,0.3580083,0.0003435921,0.0002275036,0.0002961339,0.02316099,0.003057732,0.009687255],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01347659,"threshold_uncertainty_score":0.04508364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009640851050672892,"score_gpt":0.3366817382973911,"score_spread":0.3270408872467181,"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."}}