{"id":"W4312380174","doi":"10.1109/ijcnn55064.2022.9891933","title":"Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); École de Technologie Supérieure","funders":"","keywords":"Pascal (unit); Ground truth; Artificial intelligence; Computer science; Minimum bounding box; Annotation; Machine learning; Bounding overwatch; Object detection; Object (grammar); Source code; Pattern recognition (psychology); Natural language processing; Image (mathematics)","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":[0.004405307,0.002383873,0.002078445,0.001424502,0.0006855371,0.00215912,0.004341648,0.002846686,0.003079006],"category_scores_gemma":[0.01395874,0.001125003,0.001409554,0.001035195,0.001789927,0.004001492,0.003270381,0.002414661,0.004344842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001307544,"about_ca_system_score_gemma":0.001391673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00423603,"about_ca_topic_score_gemma":0.006264759,"domain_scores_codex":[0.9952579,0.001539999,0.0001880375,0.001574246,0.001081924,0.0003578531],"domain_scores_gemma":[0.9882606,0.004876265,0.0007682789,0.003725147,0.001943971,0.0004257218],"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":[0.002087795,0.0006366055,0.01127841,0.0004281114,0.0002132756,0.0003604365,0.0004153702,0.2850855,0.03850373,0.006686503,0.02008416,0.6342202],"study_design_scores_gemma":[0.00002144066,0.00006014978,0.0006987262,0.0000159159,0.00001241605,0.0001155295,0.00003381696,0.9821801,0.01204533,0.003544966,0.001257606,0.00001401994],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06792201,0.0003370201,0.9171671,0.0001606367,0.00007092739,0.0002193122,0.0007167513,0.01172299,0.001683175],"genre_scores_gemma":[0.4379445,0.0001621823,0.5486577,0.0002657873,0.00007183988,0.0002885957,0.007582538,0.0009028417,0.004123921],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004405307,"threshold_uncertainty_score":0.02329779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03577843570185908,"score_gpt":0.267846178377684,"score_spread":0.2320677426758249,"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."}}