{"id":"W2965182628","doi":"10.1109/cvpr.2019.00902","title":"UPSNet: A Unified Panoptic Segmentation Network","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":422,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Inference; Convolution (computer science); Representation (politics); Task (project management); Computer vision; Class (philosophy); Pixel; Panopticon; Image segmentation; Code (set theory); Pattern recognition (psychology); Artificial neural network; Programming language","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":[0.0001340404,0.0002614602,0.0002383509,0.00006285414,0.0000963924,0.0001848291,0.001443691,0.0001459801,0.00002023842],"category_scores_gemma":[0.000007798254,0.0002556071,0.00009317126,0.0003863581,0.00002501646,0.0001528839,0.001935387,0.000468716,0.0004183851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008338453,"about_ca_system_score_gemma":0.0001276723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000622054,"about_ca_topic_score_gemma":0.000007797677,"domain_scores_codex":[0.9981638,0.00006718429,0.0003186099,0.0008276855,0.0002627559,0.0003599876],"domain_scores_gemma":[0.9977758,0.0001228073,0.0002460472,0.001683551,0.00008378336,0.00008799956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003974516,0.00003330195,0.0002351374,0.0000470455,0.00002626921,0.00000157599,0.00008025038,0.7997379,0.0001521763,0.1360326,0.01281696,0.05083283],"study_design_scores_gemma":[0.000376842,0.00005962483,0.00202039,0.0001266134,0.00003121598,0.000008736715,0.000009289623,0.7536798,0.0004880211,0.2156025,0.02665136,0.0009456317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001033438,0.000457421,0.988601,0.0007463043,0.001372101,0.00100082,0.000002268956,0.0004885799,0.006298119],"genre_scores_gemma":[0.2025131,0.0004848464,0.7900978,0.001230885,0.00083439,0.0004564421,0.0001349239,0.00004992191,0.004197771],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2014796,"threshold_uncertainty_score":0.9999896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02628135047772449,"score_gpt":0.2801040390594792,"score_spread":0.2538226885817547,"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."}}