{"id":"W4380358040","doi":"10.3390/s23125488","title":"DAssd-Net: A Lightweight Steel Surface Defect Detection Model Based on Multi-Branch Dilated Convolution Aggregation and Multi-Domain Perception Detection Head","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Shanghai Municipal Education Commission; Science and Technology Commission of Shanghai Municipality; Natural Science Foundation of Shanghai","keywords":"Convolution (computer science); Computer science; Feature (linguistics); Artificial intelligence; Redundancy (engineering); Channel (broadcasting); Pattern recognition (psychology); Computer vision; Artificial neural network","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":[0.0003099535,0.000845388,0.0006086436,0.0005250258,0.0002092802,0.0005265679,0.001678412,0.0006387517,0.002116177],"category_scores_gemma":[0.0006525313,0.000378326,0.0008978744,0.0003174017,0.0002692491,0.0008658143,0.0007383241,0.0008009383,0.0007717593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008332533,"about_ca_system_score_gemma":0.0007525256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01172014,"about_ca_topic_score_gemma":0.01334189,"domain_scores_codex":[0.9998425,0.00001371466,0.000007616427,0.00006207339,0.00004927687,0.00002480047],"domain_scores_gemma":[0.9998327,0.00004137432,0.00001824188,0.00002324089,0.00006754156,0.00001684317],"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":[0.0004708504,0.0001844778,0.005119614,0.0001198303,0.0001719071,0.0002116378,0.00007166422,0.666586,0.02334203,0.00268117,0.007102832,0.293938],"study_design_scores_gemma":[0.000005314628,0.00002336996,0.0003026339,0.000001805675,0.00001058237,0.00002200366,0.000003037665,0.9964309,0.002189155,0.0003597382,0.0006474277,0.00000411218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0626561,0.0005820177,0.9253405,0.0002735094,0.0001406357,0.00008660414,0.0006608381,0.007309417,0.002950309],"genre_scores_gemma":[0.7524155,0.0004582115,0.2326233,0.0003344697,0.00006474978,0.0002063537,0.002085138,0.0003059431,0.01150624],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01172014,"threshold_uncertainty_score":0.02330387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02713086547484965,"score_gpt":0.2498766096970347,"score_spread":0.222745744222185,"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."}}