{"id":"W2991471181","doi":"10.1109/iccv.2019.00533","title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":737,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Benchmark (surveying); Noise (video); Computer vision; Representation (politics); Focus (optics); Pattern recognition (psychology); Boundary (topology); Architecture; Image segmentation; Image (mathematics); Mathematics","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":[0.0003402848,0.001368118,0.0007290085,0.0008014643,0.0002753673,0.0007654137,0.001925752,0.0009363118,0.005145212],"category_scores_gemma":[0.000813662,0.0004413571,0.0009168002,0.0008812189,0.0005716507,0.001451868,0.001076888,0.0009899003,0.00229421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001225468,"about_ca_system_score_gemma":0.001188567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01062908,"about_ca_topic_score_gemma":0.02030433,"domain_scores_codex":[0.9997602,0.00002193326,0.000009303404,0.00009186939,0.00006858693,0.00004822063],"domain_scores_gemma":[0.9998399,0.00002422563,0.00001823549,0.00004504499,0.00005175364,0.00002086158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006858537,0.0002373734,0.002213252,0.0003200749,0.0002470997,0.0002719219,0.0001166643,0.1674903,0.06841318,0.01686595,0.03447248,0.7086658],"study_design_scores_gemma":[0.00003081035,0.00007894907,0.001082517,0.00002779388,0.00004670178,0.0001340983,0.00002713533,0.9481862,0.02962952,0.01166886,0.00906549,0.00002191718],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06705214,0.001561527,0.8907791,0.0004802425,0.0004973474,0.0002182449,0.003176028,0.02192114,0.0143143],"genre_scores_gemma":[0.5286368,0.001077577,0.4295126,0.001102559,0.0001670464,0.0002365634,0.01421874,0.00159677,0.0234515],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01062908,"threshold_uncertainty_score":0.02113444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0204940933020382,"score_gpt":0.2824852809530363,"score_spread":0.2619911876509981,"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."}}