{"id":"W4200478585","doi":"10.1177/14759217211053776","title":"Efficient attention-based deep encoder and decoder for automatic crack segmentation","year":2021,"lang":"en","type":"article","venue":"Structural Health Monitoring","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":291,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; Segmentation; Upsampling; Artificial intelligence; Encoder; Activation function; Ground truth; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Computer vision; Image (mathematics)","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":[0.0001132139,0.0002006769,0.0002238482,0.00007284546,0.0003065019,0.00007160676,0.00006033024,0.00006835774,0.00001271997],"category_scores_gemma":[0.00002985433,0.000196521,0.0000602839,0.0001362861,0.00002205734,0.00007296631,0.00001877306,0.0001457926,0.000001928987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002867602,"about_ca_system_score_gemma":0.00006937711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001290265,"about_ca_topic_score_gemma":0.000008834772,"domain_scores_codex":[0.9987279,0.00002505183,0.0003454077,0.0002471076,0.0001767909,0.0004777696],"domain_scores_gemma":[0.9994405,0.00008599672,0.00006609441,0.0001598496,0.0001082508,0.0001393367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002380037,0.00001140476,0.03836232,0.003433428,0.0000995829,0.0000142433,0.002169876,0.532668,0.03576472,0.0001502304,0.0001155195,0.3871869],"study_design_scores_gemma":[0.001044614,0.00004922328,0.09470958,0.0003018658,0.00002493454,0.00002385024,0.001023777,0.8754972,0.02654671,0.0002957488,0.0001265743,0.0003559038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9544501,0.001208726,0.03970364,0.0001153813,0.003886644,0.0003547588,0.0000134183,0.0002369623,0.00003035172],"genre_scores_gemma":[0.9382631,0.00002376731,0.06092549,0.00004537034,0.0005937083,0.00006276902,0.0000266189,0.00003919861,0.0000199292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.386831,"threshold_uncertainty_score":0.8013892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01061468104800626,"score_gpt":0.2870019397863203,"score_spread":0.276387258738314,"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."}}