{"id":"W3034512672","doi":"10.1109/cvpr42600.2020.00915","title":"PolyTransform: Deep Polygon Transformer for Instance Segmentation","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":185,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Segmentation; Polygon (computer graphics); Computer science; Artificial intelligence; Exploit; Image segmentation; Scale-space segmentation; Computer vision; Segmentation-based object categorization; 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":[0.00003301823,0.0001018538,0.0000958583,0.00002149233,0.0001183504,0.0000424723,0.0004012583,0.00002931843,0.00001539273],"category_scores_gemma":[0.000005080197,0.00009340253,0.00005769388,0.0003891711,0.00001834228,0.0006648338,0.00001116758,0.00005787504,0.00003226607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002068935,"about_ca_system_score_gemma":0.00001875815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000187978,"about_ca_topic_score_gemma":0.00001330939,"domain_scores_codex":[0.9991657,0.000007123146,0.0001786756,0.0003035027,0.0001273843,0.0002175851],"domain_scores_gemma":[0.9995909,0.00004931342,0.00003346226,0.0001717792,0.00003655126,0.0001179969],"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":[0.00004078839,0.00003954105,0.00004556398,0.000031707,0.00001449849,7.701635e-7,0.001629459,0.00215403,0.08295698,0.3988468,0.0009820482,0.5132579],"study_design_scores_gemma":[0.00171684,0.0003588492,0.0002575018,0.000007929231,0.00001615195,0.000006848954,0.0001580384,0.5835675,0.3405879,0.02033716,0.05242629,0.0005590316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001035634,0.00007333893,0.9790952,0.01639874,0.00005639423,0.0006226221,0.000004241042,0.0002874591,0.002426369],"genre_scores_gemma":[0.5752575,0.00004541209,0.4175997,0.006686072,0.00008319988,0.0001936062,0.00001007409,0.00001234154,0.0001120696],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5814134,"threshold_uncertainty_score":0.3808845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02691956037334562,"score_gpt":0.2710345626970707,"score_spread":0.244115002323725,"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."}}