{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003589157,0.0001148693,0.0001495252,0.0003003697,0.00004696259,0.0003401225,0.001100958,0.0000377847,0.00001309056],"category_scores_gemma":[0.00001986736,0.00009735455,0.0001274398,0.0001688136,0.00001858556,0.002379709,0.0001444548,0.0001760208,0.000009069953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009900764,"about_ca_system_score_gemma":0.00003868243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.756815e-7,"about_ca_topic_score_gemma":6.182438e-8,"domain_scores_codex":[0.9984774,0.00004682225,0.0004654165,0.0001670504,0.0007130026,0.0001303056],"domain_scores_gemma":[0.998561,0.00006715195,0.0004099606,0.0001542225,0.0007350297,0.00007264226],"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":[0.00002359619,0.00007981337,0.00002202787,0.000001018787,0.00001817759,0.0001879055,0.0001174097,0.00009253372,0.01531741,0.001526836,0.001832769,0.9807805],"study_design_scores_gemma":[0.003721153,0.007122693,0.02601996,0.0009345375,0.00003045648,0.003725861,0.00002790809,0.3530314,0.4675198,0.09889115,0.03803089,0.0009441457],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003607967,0.00008933101,0.9926968,0.001836561,0.001387591,0.00005629119,7.60064e-7,0.00005990127,0.00026476],"genre_scores_gemma":[0.2168669,0.0001329864,0.7810909,0.0009716203,0.0009152844,3.005916e-7,0.000002407665,0.000004332749,0.00001519925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9798363,"threshold_uncertainty_score":0.3970003,"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."}}