{"id":"W4310921857","doi":"10.48550/arxiv.2212.03338","title":"Framework-agnostic Semantically-aware Global Reasoning for Segmentation","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Pixel; Representation (politics); Semantics (computer science); Object (grammar); Transformer; Natural language processing; Pattern recognition (psychology); Machine learning","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":[0.001205654,0.001241868,0.0009299287,0.0009751042,0.0004344209,0.00151663,0.002812781,0.001263668,0.004018007],"category_scores_gemma":[0.002299058,0.0005576759,0.00173732,0.0008844218,0.001174005,0.004009608,0.002270042,0.002237862,0.001574037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001536447,"about_ca_system_score_gemma":0.001696564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006585846,"about_ca_topic_score_gemma":0.01310739,"domain_scores_codex":[0.9993535,0.00009810133,0.00003222107,0.0002548266,0.000170147,0.00009131658],"domain_scores_gemma":[0.9993854,0.0001543604,0.00005256274,0.0002564185,0.0001041322,0.00004719938],"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":[0.0004850838,0.0002936537,0.002069317,0.0003988862,0.0002244925,0.000309393,0.0004595192,0.2527364,0.0723028,0.05130464,0.01234846,0.6070674],"study_design_scores_gemma":[0.00002011217,0.00006020166,0.0003576853,0.00001831734,0.00005023493,0.00008374576,0.00005063834,0.9320518,0.01889408,0.04507941,0.003316475,0.00001732664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01367375,0.000287935,0.9746343,0.0001730851,0.00003632305,0.00007622637,0.0003834382,0.009040106,0.001694887],"genre_scores_gemma":[0.3954435,0.0003707138,0.596553,0.0003545059,0.00004960542,0.0001029411,0.002643977,0.0008775815,0.003604187],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006585846,"threshold_uncertainty_score":0.01344156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05530222993116807,"score_gpt":0.2529445417316458,"score_spread":0.1976423118004777,"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."}}