{"id":"W4200099838","doi":"10.32920/17312189","title":"Unsupervised Panoptic Segmentation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"University of Toronto","keywords":"Panopticon; Computer science; Segmentation; Cluster analysis; Artificial intelligence; Visual cortex; Unsupervised learning; Code (set theory); Set (abstract data type); Image segmentation; Computer vision; Image (mathematics); Pattern recognition (psychology); Psychology; Neuroscience; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00003206058,0.0001249068,0.0001117808,0.00003813222,0.00002728549,0.0001454188,0.0001269438,0.0001199492,0.0002194217],"category_scores_gemma":[0.000002762736,0.0001326089,0.00004796209,0.00007215571,0.000009439133,0.0000460133,0.0001096761,0.0002177245,0.00001844854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004897936,"about_ca_system_score_gemma":0.00002610209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001108172,"about_ca_topic_score_gemma":0.000002772513,"domain_scores_codex":[0.999523,0.000004911908,0.0001405261,0.000157735,0.0000731406,0.0001006355],"domain_scores_gemma":[0.9996327,0.000006735242,0.00001481899,0.00027218,0.00004624976,0.00002731866],"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":[0.000003367174,0.0002421945,0.0002665323,0.006352428,0.0003937387,0.00003258044,0.002313644,0.1108783,0.4550267,0.002891214,0.03405271,0.3875466],"study_design_scores_gemma":[0.0001984278,0.0000085727,0.0002916306,0.0003410696,0.0001051906,0.000008925245,0.0003531101,0.5453756,0.4437274,0.005504169,0.003159567,0.0009262606],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03956994,0.0007432762,0.9342091,0.0001388926,0.0001821824,0.0002642355,0.000007916839,0.002356034,0.02252841],"genre_scores_gemma":[0.6927398,0.0003269743,0.3057667,0.00007835927,0.00006274929,0.0002995954,0.0002782073,0.00004279843,0.0004047683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6531699,"threshold_uncertainty_score":0.5407634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01685564448515926,"score_gpt":0.2556399365493213,"score_spread":0.238784292064162,"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."}}