{"id":"W4413156257","doi":"10.1109/cvpr52734.2025.02363","title":"WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Computer science; Artificial intelligence; Segmentation; Image segmentation; Pattern recognition (psychology); Computer vision","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":[0.002716672,0.00234912,0.002317952,0.001941117,0.001058034,0.0028442,0.005198509,0.002765621,0.003562227],"category_scores_gemma":[0.00585191,0.001085709,0.002000996,0.001826975,0.001918586,0.004363749,0.004079095,0.00384443,0.002812071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314092,"about_ca_system_score_gemma":0.002019833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00383588,"about_ca_topic_score_gemma":0.00919876,"domain_scores_codex":[0.9974436,0.0005948664,0.000103194,0.001097197,0.0005270083,0.0002341926],"domain_scores_gemma":[0.9971074,0.0008552033,0.000301571,0.001091383,0.000427486,0.0002169812],"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":[0.001076818,0.0006370505,0.006520297,0.0004953467,0.0003780007,0.0004358049,0.0005702068,0.1923811,0.04584879,0.03332506,0.03661007,0.6817214],"study_design_scores_gemma":[0.00003042653,0.00006201633,0.000495587,0.0000224894,0.00003088417,0.0001155646,0.00005875587,0.9654347,0.009774741,0.01983126,0.004119378,0.00002411773],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008462808,0.0001793239,0.984413,0.0001582944,0.00003931199,0.0001105685,0.0003141241,0.005193807,0.001128759],"genre_scores_gemma":[0.2150738,0.0002274896,0.7707579,0.0007451417,0.0001730912,0.0003910096,0.004129938,0.001942983,0.006558627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005198509,"threshold_uncertainty_score":0.01436734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02255794911329053,"score_gpt":0.2948717356388346,"score_spread":0.2723137865255441,"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."}}