{"id":"W4360989175","doi":"10.18280/ria.370108","title":"Efficient Method Using Attention Based Convolutional Neural Networks for Ceramic Tiles Defect Classification","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); Ceramic tiles; Ceramic; Materials science; Metallurgy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004899232,0.001033113,0.0008600664,0.00168496,0.0002567951,0.0005554786,0.001591153,0.001070379,0.001230838],"category_scores_gemma":[0.0007805664,0.0002926211,0.0009201093,0.0007875549,0.0003064209,0.0007254125,0.0006822408,0.0007625402,0.0005702513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007793786,"about_ca_system_score_gemma":0.001032653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01158777,"about_ca_topic_score_gemma":0.01121132,"domain_scores_codex":[0.9996393,0.00003181623,0.00002254794,0.0001191669,0.0001102806,0.0000769617],"domain_scores_gemma":[0.9995705,0.00009897006,0.00005673328,0.00006210559,0.000182138,0.00002951694],"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":[0.0006651829,0.0003246784,0.005766462,0.0001714318,0.00014158,0.0002731489,0.00007277648,0.1117932,0.05701037,0.001513486,0.006836372,0.8154312],"study_design_scores_gemma":[0.00001362513,0.00005590289,0.001481026,0.000007245243,0.0000373572,0.00008759269,0.0000136624,0.9856384,0.01137761,0.0005014375,0.0007767913,0.000009339434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1770321,0.001250108,0.8121809,0.0003087155,0.0001603397,0.0001847442,0.0004586426,0.005656908,0.002767495],"genre_scores_gemma":[0.8012853,0.0005268585,0.1878874,0.0002498457,0.00009782615,0.0001344698,0.001725246,0.0001559835,0.007937108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01158777,"threshold_uncertainty_score":0.02304065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09965376628126603,"score_gpt":0.3207964429939459,"score_spread":0.2211426767126799,"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."}}