{"id":"W4411399751","doi":"10.1016/j.patcog.2025.111975","title":"Refining pseudo-labels through iterative mix-up for weakly supervised semantic segmentation","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Training Program for Excellent Young Innovators of Changsha; Higher Education Discipline Innovation Project; Natural Science Foundation of Hunan Province; National Science Foundation","keywords":"Refining (metallurgy); Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Natural language processing; Computer vision; Materials science","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":[0.002063853,0.002571336,0.002028235,0.001777834,0.001170036,0.002224442,0.003396974,0.002384972,0.003355604],"category_scores_gemma":[0.005912408,0.001241876,0.001834282,0.001236273,0.00240227,0.003303936,0.005194848,0.002707016,0.002752296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001165018,"about_ca_system_score_gemma":0.001768488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003064987,"about_ca_topic_score_gemma":0.007120417,"domain_scores_codex":[0.9980196,0.0004262581,0.0001017066,0.0006497758,0.0005708187,0.0002318219],"domain_scores_gemma":[0.9972427,0.0009847622,0.000263461,0.0007648527,0.0005742101,0.0001700841],"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":[0.00134023,0.0003597519,0.003369027,0.0004344382,0.0002134755,0.0003883826,0.00107135,0.2658805,0.1238832,0.0155605,0.007558449,0.5799406],"study_design_scores_gemma":[0.00003210493,0.0001031656,0.000322705,0.00001973246,0.00003115372,0.00009918711,0.0000829811,0.9566473,0.02667729,0.01346283,0.002488558,0.00003297091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03346705,0.0001995141,0.9599212,0.0001488887,0.00004548681,0.0001078363,0.0001328666,0.004763006,0.001214195],"genre_scores_gemma":[0.2773362,0.0001569976,0.714465,0.0004395899,0.00007139691,0.0003661199,0.001337687,0.001984017,0.003842886],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003396974,"threshold_uncertainty_score":0.01122558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05057411921813759,"score_gpt":0.3192396139583518,"score_spread":0.2686654947402142,"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."}}