{"id":"W2979396152","doi":"10.1109/tie.2019.2945265","title":"SDDNet: Real-Time Crack Segmentation","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":445,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Pyramid (geometry); Pooling; Convolutional neural network; Convolution (computer science); Pattern recognition (psychology); Intersection (aeronautics); Pixel; Range (aeronautics); Image segmentation; Artificial neural network; Test set; Set (abstract data type); Computer vision; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00008932696,0.0001877498,0.0001738987,0.0001170071,0.00007963012,0.00003811768,0.0001106624,0.0002268966,0.0004356645],"category_scores_gemma":[0.000001594385,0.0001954875,0.00008264892,0.0002344858,0.00001333135,0.0001734313,4.21917e-7,0.0006006432,0.0004584523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004118698,"about_ca_system_score_gemma":0.00007664361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001830097,"about_ca_topic_score_gemma":0.000008579506,"domain_scores_codex":[0.9989736,0.00002105708,0.0002192775,0.0001810583,0.0001826721,0.0004223539],"domain_scores_gemma":[0.9996199,0.00004138715,0.00003127913,0.0002154486,0.00003030694,0.00006165857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001226874,0.00003565272,0.00002382825,0.00001764515,0.0001450697,0.000002621749,0.0001852371,0.6386216,0.2814845,0.0001071301,0.002382114,0.07687191],"study_design_scores_gemma":[0.002625917,0.0005810448,0.00003250162,0.00007606674,0.00009071216,0.00001652102,0.0001127318,0.02947618,0.9501908,0.0001915985,0.01597209,0.0006337836],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9162999,0.00004852033,0.06628868,0.00006194022,0.006079489,0.0007506433,0.00003255311,0.0007926019,0.009645613],"genre_scores_gemma":[0.9974416,0.0001965686,0.0002428037,0.00002379061,0.0003851335,0.00003130735,0.000008863526,0.00005647506,0.001613449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6687064,"threshold_uncertainty_score":0.7971749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008833765349411759,"score_gpt":0.2109811786882521,"score_spread":0.2021474133388403,"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."}}