{"id":"W2972118985","doi":"10.48550/arxiv.1909.03402","title":"Squeeze-and-Attention Networks for Semantic Segmentation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China","keywords":"Pascal (unit); Segmentation; Computer science; Artificial intelligence; Pixel; Convolution (computer science); Context (archaeology); Channel (broadcasting); Pattern recognition (psychology); Machine learning; Artificial neural network; Geography; Telecommunications","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":[0.0004769406,0.001093369,0.0006226033,0.0007420081,0.0003749191,0.0007745536,0.001429917,0.00111868,0.003497559],"category_scores_gemma":[0.001144889,0.0005479852,0.0007153446,0.0007378763,0.0008459698,0.00214426,0.001229739,0.001430116,0.000840746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00120923,"about_ca_system_score_gemma":0.0009140313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009193406,"about_ca_topic_score_gemma":0.0152378,"domain_scores_codex":[0.9997404,0.00003771719,0.000009822691,0.0001170722,0.0000453195,0.00004971922],"domain_scores_gemma":[0.9997242,0.0001127876,0.00003234998,0.000054615,0.00005120515,0.00002479983],"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":[0.0006020724,0.000171483,0.001651941,0.0002422332,0.0001978823,0.0002190782,0.0002603943,0.3539487,0.0699381,0.02751604,0.00761789,0.5376341],"study_design_scores_gemma":[0.00000911176,0.00004826046,0.000546817,0.00001370221,0.0000349133,0.00004437071,0.00002060779,0.9709273,0.0120399,0.01393216,0.002369408,0.00001349838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05818954,0.001820209,0.9291328,0.0004685494,0.0001256193,0.00005782032,0.0003301227,0.004866662,0.005008837],"genre_scores_gemma":[0.7264366,0.001052786,0.2610474,0.0005249566,0.0001080694,0.0001025662,0.001001453,0.000359861,0.009366422],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009193406,"threshold_uncertainty_score":0.01827979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05327513775965514,"score_gpt":0.2117727453032028,"score_spread":0.1584976075435476,"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."}}