{"id":"W4412394752","doi":"10.1007/978-981-96-9949-0_38","title":"MCT-Net: Multiscale Convolution-Transformer Network for Defect Image Generation Using Segmentation Maps","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Convolution (computer science); Transformer; Artificial intelligence; Segmentation; Computer vision; Pattern recognition (psychology); Electrical engineering; Engineering; Artificial neural network; Voltage","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008025643,0.0001975061,0.0002281824,0.0005616188,0.0005660686,0.0003112689,0.0003487731,0.0002010528,0.000006722356],"category_scores_gemma":[0.00001953859,0.0002125745,0.00007930564,0.0002902532,0.0001997884,0.002509724,0.00009290763,0.0002509444,0.0000115188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002959353,"about_ca_system_score_gemma":0.000117664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002307352,"about_ca_topic_score_gemma":0.00003150648,"domain_scores_codex":[0.998712,0.0000226705,0.0006900248,0.0001635558,0.0002099217,0.0002018214],"domain_scores_gemma":[0.9988172,0.0001280915,0.0001530576,0.0005463008,0.0003053826,0.00004994493],"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":[0.00003326055,0.00002454361,0.00007822419,0.0005325526,0.00009746492,2.575978e-7,0.002312406,0.2375258,0.002537283,0.09567945,0.01695673,0.6442221],"study_design_scores_gemma":[0.000450067,0.00003014642,0.00004293621,0.0002174138,0.00002172356,0.000005709413,0.00001902317,0.9108215,0.0002141006,0.0004975278,0.08744852,0.0002313423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003310632,0.0005333848,0.9571772,0.00003885334,0.001322778,0.001243134,0.0001108145,0.0001149805,0.03912779],"genre_scores_gemma":[0.2461494,0.007082157,0.7342677,0.0009783568,0.002047981,0.0007200911,0.00353834,0.0001310753,0.005084889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6732957,"threshold_uncertainty_score":0.8668537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04591637960413585,"score_gpt":0.2915973830434393,"score_spread":0.2456810034393034,"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."}}