{"id":"W4391093474","doi":"10.1109/bigdata59044.2023.10386451","title":"Lightweight CNN based on Spatial Features for a Vehicular Damage Detection System","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"Silesian University of Technology","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Regularization (linguistics); Automotive industry; Key (lock); Transfer of learning; Dropout (neural networks); Architecture; Computer vision; Machine learning; Pattern recognition (psychology); Engineering; Computer security","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":[0.0001527327,0.0004373993,0.000282175,0.0003149234,0.0001954597,0.0003499408,0.0008048586,0.0004207823,0.002133912],"category_scores_gemma":[0.000379375,0.0002202949,0.000280118,0.0002787263,0.000153893,0.0005700223,0.0004146282,0.0003950864,0.0007524869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007337501,"about_ca_system_score_gemma":0.0004996003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01027187,"about_ca_topic_score_gemma":0.01363383,"domain_scores_codex":[0.9998962,0.000005955345,0.000005357851,0.00003099087,0.00003699965,0.00002455967],"domain_scores_gemma":[0.9999042,0.00001283314,0.00001277317,0.00001978508,0.00004340704,0.00000702257],"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":[0.0004964272,0.0002910825,0.005749726,0.0001804776,0.0001643979,0.0004542834,0.00005545633,0.3891494,0.1292935,0.004103835,0.008638718,0.4614227],"study_design_scores_gemma":[0.000005441434,0.00006647642,0.001558053,0.00000829794,0.00002607799,0.00006763729,0.000006931245,0.9795476,0.01645122,0.0006353536,0.001618059,0.000008798255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3556947,0.0009625448,0.6228153,0.0005350675,0.0003158672,0.000154888,0.001142936,0.007465205,0.01091361],"genre_scores_gemma":[0.9298725,0.0002046625,0.0628029,0.0001384157,0.00003051574,0.00006430406,0.0008309618,0.00004290254,0.006012869],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01027187,"threshold_uncertainty_score":0.02042419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01255519269465848,"score_gpt":0.2475244244614776,"score_spread":0.2349692317668191,"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."}}