{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026968,0.000285301,0.0002697202,0.0001195985,0.0004514644,0.0001691581,0.001970168,0.0002301448,0.00009011586],"category_scores_gemma":[0.0002760654,0.0003727405,0.000210672,0.000664396,0.00005740285,0.0002020183,0.002418846,0.0007538914,0.00005177168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000551308,"about_ca_system_score_gemma":0.0002176141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003976158,"about_ca_topic_score_gemma":0.00001833515,"domain_scores_codex":[0.9978462,0.0001685253,0.0002130675,0.001263905,0.0001401526,0.0003681344],"domain_scores_gemma":[0.9976268,0.0005256723,0.0002915595,0.001249011,0.0001479412,0.0001589677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001381556,0.0000745733,0.0145129,0.00006540168,0.00005247133,0.00002877473,0.0001253947,0.4756604,0.000005441684,0.508255,0.0001178913,0.001087929],"study_design_scores_gemma":[0.000279988,0.00005055663,0.01052467,0.00007071052,0.00007758845,0.000003515482,0.00005714193,0.8581185,0.0000093768,0.1301855,0.0002631688,0.0003593388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09530284,0.00002290869,0.9018183,0.0005034813,0.0004310217,0.0007477701,0.00007953599,0.0004626785,0.0006314697],"genre_scores_gemma":[0.9019002,0.00002182857,0.09749053,0.0001730524,0.0000719757,0.00002616501,0.000117165,0.00001949426,0.0001795623],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8065974,"threshold_uncertainty_score":0.9998724,"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."}}