{"id":"W3034681889","doi":"10.1109/cvpr42600.2020.01308","title":"Squeeze-and-Attention Networks for Semantic Segmentation","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":330,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pascal (unit); Segmentation; Computer science; Artificial intelligence; Pixel; Convolution (computer science); Context (archaeology); Pattern recognition (psychology); Grid; Image segmentation; Machine learning; Artificial neural network; 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":[0.0004706283,0.001059544,0.0006107646,0.0006981163,0.0003591334,0.0007479728,0.001377222,0.001099269,0.003441031],"category_scores_gemma":[0.001104694,0.0005459061,0.000678089,0.0007159113,0.000841752,0.002120541,0.00121575,0.001425745,0.0007953126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001170253,"about_ca_system_score_gemma":0.0008878646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0087015,"about_ca_topic_score_gemma":0.0147445,"domain_scores_codex":[0.9997478,0.00003683384,0.000009495921,0.000111132,0.00004593726,0.00004877913],"domain_scores_gemma":[0.9997314,0.0001111893,0.00003144231,0.00005287037,0.00004920715,0.00002390064],"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":[0.000583637,0.0001616474,0.001498348,0.0002422821,0.0001920907,0.0002138232,0.0002442464,0.3568962,0.07709278,0.02744154,0.007204818,0.5282285],"study_design_scores_gemma":[0.000008853763,0.0000453632,0.0005108975,0.0000125627,0.00003184698,0.00004301517,0.00001905213,0.9713082,0.01275547,0.01294466,0.002307199,0.00001278506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05325178,0.001705452,0.9351048,0.0004215641,0.0001157637,0.00005300616,0.0002841344,0.004465673,0.004597839],"genre_scores_gemma":[0.7159478,0.001044243,0.2718661,0.0005071553,0.0001058042,0.0000990916,0.0008967924,0.0003550648,0.009177836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0087015,"threshold_uncertainty_score":0.01730174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03345037281667305,"score_gpt":0.2995651833011245,"score_spread":0.2661148104844515,"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."}}