{"id":"W2510758617","doi":"10.1109/icip.2016.7532453","title":"Shape-included label-consistent discriminative dictionary learning: An approach to detect and segment multi-class objects in images","year":2016,"lang":"en","type":"article","venue":"","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Discriminative model; Artificial intelligence; Pattern recognition (psychology); Segmentation; Computer science; Representation (politics); Sparse approximation; Object (grammar); Dictionary learning; Image segmentation; 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":[0.0003067507,0.0001874708,0.0002222821,0.0002250297,0.00009159155,0.00004559402,0.00006090299,0.0001200731,0.00002205869],"category_scores_gemma":[0.00006896151,0.0001276837,0.00003355799,0.0001904657,0.00002404731,0.0002198676,0.0000583035,0.0001578435,0.0000251659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001853572,"about_ca_system_score_gemma":0.00001155324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009196896,"about_ca_topic_score_gemma":0.00005526327,"domain_scores_codex":[0.9988778,0.0001162153,0.0002696126,0.0003139986,0.0001729889,0.0002493614],"domain_scores_gemma":[0.9995633,0.00008097247,0.00002979629,0.000140514,0.00004276482,0.0001426016],"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":[0.0002710706,0.0002905905,0.002492971,0.0001587185,0.0001403551,0.00002733868,0.004743156,0.009013229,0.4611832,0.0001907684,0.0006786988,0.5208098],"study_design_scores_gemma":[0.02073812,0.003974347,0.1204779,0.001019999,0.0001247884,0.0002576536,0.01944967,0.4464215,0.3765628,0.000257173,0.007296919,0.003419097],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9373164,0.0001153653,0.04998004,0.00007153844,0.0004322322,0.0008354156,0.00001211045,0.0005268229,0.01071012],"genre_scores_gemma":[0.996675,0.00001647461,0.002160982,0.00002156105,0.00007666348,0.000107088,0.000002570454,0.00003042252,0.0009093026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5173907,"threshold_uncertainty_score":0.520679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0382952671877906,"score_gpt":0.2599637961558429,"score_spread":0.2216685289680523,"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."}}