{"id":"W3032959347","doi":"10.1109/access.2020.2999596","title":"Weakly Supervised Object Detection Using Complementary Learning and Instance Clustering","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Iran Telecommunication Research Center; National Research Foundation of Korea; Information Technology Research Centre; National Research Foundation","keywords":"Computer science; Cluster analysis; Artificial intelligence; Discriminative model; Pattern recognition (psychology); Pascal (unit); Object detection; Centroid; Object (grammar); Class (philosophy); Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005080219,0.0001043833,0.0001092479,0.00003609896,0.0002922296,0.0001949411,0.0004822336,0.00002163728,0.000004863179],"category_scores_gemma":[0.00001000692,0.0001140913,0.0000199158,0.0004774839,0.00002559344,0.001090126,0.0003456729,0.0001649983,0.000004094247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003370931,"about_ca_system_score_gemma":0.0000120295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003362734,"about_ca_topic_score_gemma":0.00005733987,"domain_scores_codex":[0.9991252,0.00004269962,0.000159577,0.0003580251,0.0001238227,0.0001906859],"domain_scores_gemma":[0.9995981,0.00005896428,0.00007413226,0.0001509836,0.00002967274,0.00008810507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005187053,0.00003371657,0.01381704,0.000120541,0.00003681075,0.00002806589,0.001852685,0.1968905,0.4574356,0.0004848625,0.00008175054,0.3291665],"study_design_scores_gemma":[0.0002223934,0.00003417147,0.001223132,0.00001396266,0.000004495333,0.00001152169,0.00003140211,0.9781461,0.01834486,0.0002681845,0.001545193,0.0001545568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3183094,0.00005112483,0.6807936,0.0003844463,0.00009719113,0.0001309868,6.738464e-7,0.0001543438,0.0000782831],"genre_scores_gemma":[0.975231,0.00003060886,0.02380891,0.0007727171,0.0001280744,0.00001278928,0.000001042755,0.00001123825,0.000003615559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7812556,"threshold_uncertainty_score":0.4652507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07110817050395161,"score_gpt":0.3278329014385207,"score_spread":0.2567247309345691,"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."}}