{"id":"W4285604884","doi":"10.24963/ijcai.2022/389","title":"One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Western Canada Research Grid; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Segmentation; Classifier (UML); Artificial intelligence; Hyperparameter; Pattern recognition (psychology); Pixel; Image segmentation; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000501606,0.0002874269,0.0002972458,0.0003233354,0.0005894069,0.000251463,0.003276229,0.00005533317,0.0001282614],"category_scores_gemma":[0.0002046634,0.0002732318,0.0001785381,0.0009500072,0.0001081101,0.0006035674,0.001619534,0.0005158938,0.0001160266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003487234,"about_ca_system_score_gemma":0.0001201344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004018609,"about_ca_topic_score_gemma":0.00001372632,"domain_scores_codex":[0.9966063,0.00002552993,0.0008549038,0.0008216781,0.001290909,0.000400643],"domain_scores_gemma":[0.9979351,0.0001018239,0.0005617261,0.0004361953,0.0008170667,0.0001481137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001149041,0.0003864575,0.00005109708,0.00002208739,0.00003713773,3.743111e-7,0.001769593,0.05661092,0.238141,0.6755478,0.0003451732,0.0269734],"study_design_scores_gemma":[0.00005659283,0.000185632,0.00008850235,0.00005848747,0.0000127342,0.00000601797,0.0005021407,0.6279014,0.210611,0.1601418,0.0001754122,0.0002603649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1295899,0.00001730045,0.8105054,0.04981745,0.001823376,0.00198916,0.00008509158,0.0003178777,0.005854378],"genre_scores_gemma":[0.9716387,0.00002807277,0.0258781,0.001216837,0.0001464801,0.0004483547,0.000005503791,0.00002600208,0.0006119803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8420487,"threshold_uncertainty_score":0.999972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.090667810114998,"score_gpt":0.3025308155715213,"score_spread":0.2118630054565233,"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."}}