{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001486934,0.00008010212,0.00007778474,0.00009388891,0.0001331162,0.000174783,0.0003988141,0.00003379565,0.00002349079],"category_scores_gemma":[0.00002907808,0.00007503177,0.00002365297,0.0004034544,0.00001571906,0.0003982771,0.0001081178,0.00007076727,0.00003108836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005119114,"about_ca_system_score_gemma":0.00005971647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008756654,"about_ca_topic_score_gemma":0.0000247363,"domain_scores_codex":[0.9992229,0.00006908681,0.0001585018,0.0002834796,0.0001304828,0.0001354953],"domain_scores_gemma":[0.9994068,0.00003868471,0.00004425962,0.0004290606,0.00004959626,0.0000315579],"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":[0.00001977233,0.0001965125,0.01642363,0.00009710206,0.00006405337,0.00001259605,0.0007765185,0.008046365,0.2204744,0.2822894,0.002225526,0.4693741],"study_design_scores_gemma":[0.0003769624,0.0000270015,0.004350157,0.00003243275,0.000008208808,0.000007234328,0.00003911035,0.9680111,0.01870641,0.001510126,0.006756494,0.0001747178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1013631,0.00009685456,0.8903801,0.00112837,0.0002248172,0.00009931206,0.000001638329,0.0002150917,0.00649073],"genre_scores_gemma":[0.8677204,0.00001189523,0.1300851,0.0009750491,0.00001721247,0.000006596236,0.00001585895,0.000003974102,0.00116392],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9599648,"threshold_uncertainty_score":0.3059707,"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."}}