{"id":"W3192829953","doi":"10.1109/tip.2021.3102509","title":"MGSeg: Multiple Granularity-Based Real-Time Semantic Segmentation Network","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bank of Canada","funders":"Sichuan Province Science and Technology Support Program; National Natural Science Foundation of China","keywords":"Granularity; Computer science; Segmentation; Artificial intelligence; Pattern recognition (psychology); Benchmark (surveying); Feature (linguistics); Semantics (computer science); Feature extraction","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":[0.0004782945,0.001912564,0.001148948,0.0018054,0.0005251907,0.0008558921,0.001824611,0.001129987,0.004809093],"category_scores_gemma":[0.0009862873,0.0004728713,0.0008254526,0.001844462,0.0005426663,0.002252505,0.001460726,0.0008504539,0.001622734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001296935,"about_ca_system_score_gemma":0.001071328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01247667,"about_ca_topic_score_gemma":0.01732942,"domain_scores_codex":[0.9995363,0.00004635459,0.00002107072,0.000186224,0.0001258087,0.00008429807],"domain_scores_gemma":[0.9997755,0.00004053148,0.00002802414,0.00006424511,0.00006647413,0.00002528575],"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":[0.0008088539,0.0002374772,0.001541945,0.0002460749,0.0001582802,0.0002194525,0.0001658637,0.1049117,0.0297292,0.005914787,0.02140096,0.8346655],"study_design_scores_gemma":[0.00004283208,0.0001652421,0.001708774,0.0000242614,0.00006545702,0.000186325,0.00008392105,0.9594595,0.01903736,0.008649834,0.01053949,0.00003698883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06818966,0.002739316,0.8873438,0.0004146213,0.0003331033,0.0003114983,0.002551466,0.03065215,0.007464334],"genre_scores_gemma":[0.4991226,0.001400317,0.4754895,0.0004860478,0.0001590164,0.0003428955,0.01090374,0.001071964,0.01102402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01247667,"threshold_uncertainty_score":0.02480811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01531937366871666,"score_gpt":0.2683782895688636,"score_spread":0.253058915900147,"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."}}