{"id":"W4413157151","doi":"10.1109/tim.2025.3598394","title":"Dual Feature-Integration Network for Faster and More Pragmatic Few-Shot Strip Steel Surface Defect Classification","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Shot (pellet); Dual (grammatical number); Feature (linguistics); One shot; Computer science; Surface (topology); Feature extraction; Artificial intelligence; Pattern recognition (psychology); Structural engineering; Materials science; Engineering; Mechanical engineering; Geometry; Mathematics; Metallurgy","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":[0.0003112909,0.0006777673,0.0005017814,0.0004470761,0.0002278029,0.000408183,0.0009918177,0.0006225974,0.001175023],"category_scores_gemma":[0.0007344787,0.0002316018,0.0003719476,0.0003711209,0.0002448138,0.0008426472,0.0005859852,0.0007801381,0.0004415687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004880664,"about_ca_system_score_gemma":0.0006550084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005890293,"about_ca_topic_score_gemma":0.00767273,"domain_scores_codex":[0.9998046,0.0000154591,0.000007693959,0.00006246677,0.00007276805,0.00003700712],"domain_scores_gemma":[0.999744,0.00005097463,0.00003346918,0.00004032571,0.0001120839,0.00001920136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000373969,0.0002566655,0.005297929,0.00008640297,0.0000782876,0.0002568683,0.00009671949,0.1986312,0.05459393,0.002000282,0.005991207,0.7323366],"study_design_scores_gemma":[0.000007459198,0.00006923013,0.001014684,0.000003624232,0.00001590593,0.0000569016,0.00001353608,0.9901423,0.007345716,0.0005968614,0.0007250676,0.000008765613],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1815377,0.0004612526,0.8109682,0.0002070702,0.00009530148,0.00009121551,0.0002592602,0.003216553,0.00316347],"genre_scores_gemma":[0.8766153,0.0001709589,0.1172654,0.000151835,0.00003234928,0.0001044453,0.0008420466,0.00007919799,0.004738442],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005890293,"threshold_uncertainty_score":0.01171201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04806248038570873,"score_gpt":0.2759812045294622,"score_spread":0.2279187241437534,"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."}}