{"id":"W3214129952","doi":"","title":"Class-agnostic segmentation loss and its application to salient object detection and segmentation","year":2021,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Computer vision; Image segmentation; Segmentation-based object categorization; Scale-space segmentation; Class (philosophy); Object detection; Object (grammar); Salient; Pattern recognition (psychology)","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":[0.000463467,0.000140205,0.0001790428,0.0006680434,0.0008712261,0.00007507508,0.0003900021,0.00007736232,0.00002046807],"category_scores_gemma":[0.00006914871,0.0001905984,0.00006495606,0.00125855,0.0001684847,0.0009905802,0.0007718917,0.0002539677,0.00001081127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002238424,"about_ca_system_score_gemma":0.0001207883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001934081,"about_ca_topic_score_gemma":0.001181047,"domain_scores_codex":[0.9979234,0.0004191893,0.0001276984,0.00063431,0.0005572409,0.0003381712],"domain_scores_gemma":[0.9987019,0.0001876637,0.0001061933,0.0002795235,0.0004436519,0.0002810961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008094134,0.0005323893,0.009462634,0.0003842732,0.0001824682,0.0002473159,0.0121282,0.0008203594,0.6065585,0.0478514,0.0003585875,0.3206645],"study_design_scores_gemma":[0.009971204,0.0049679,0.3206161,0.0003815471,0.0002401998,0.0002596001,0.06654266,0.3817537,0.1157985,0.01571542,0.08178873,0.001964429],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5161732,0.00002340935,0.4812729,0.0008603833,0.00005342679,0.0004224741,0.00002357862,0.00005634634,0.001114301],"genre_scores_gemma":[0.989877,0.0007965882,0.008464019,0.00004657296,0.00001582189,9.894794e-7,0.00003808877,0.000007811721,0.0007531091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.49076,"threshold_uncertainty_score":0.7772378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02269993561180114,"score_gpt":0.2762443533038402,"score_spread":0.2535444176920391,"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."}}