{"id":"W2905954757","doi":"","title":"Frame Augmentation for Imbalanced Object Detection Datasets","year":2018,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Object (grammar); Artificial intelligence; Frame (networking); Exploit; Perspective (graphical); Object detection; Class (philosophy); Set (abstract data type); Computer vision; Training set; Data set; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0007621529,0.00009392889,0.0001594629,0.0002143735,0.0002263285,0.0003936734,0.000184485,0.00002414665,0.000002423821],"category_scores_gemma":[0.0001064773,0.00007940372,0.00005310008,0.000159808,0.00004541825,0.000885921,0.00003466977,0.00009177528,0.000006213684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004433708,"about_ca_system_score_gemma":0.00007170729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003131478,"about_ca_topic_score_gemma":4.587799e-7,"domain_scores_codex":[0.9988582,0.00008342912,0.0004390042,0.00013867,0.0003596037,0.0001211315],"domain_scores_gemma":[0.9986382,0.0002226858,0.0004817544,0.00008981452,0.0004822188,0.00008532527],"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":[0.0005635523,0.0003004424,0.002291101,0.0002907451,0.0002195435,0.00002257486,0.007819839,0.2472393,0.04503367,0.04521842,0.02988978,0.6211111],"study_design_scores_gemma":[0.001003313,0.000222644,0.004348377,0.00008687857,0.00000789049,0.0001942565,0.0002016118,0.983049,0.0002100826,0.003616022,0.006964373,0.00009554975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01127797,0.0001669869,0.9868659,0.0004549155,0.0009661988,0.000132074,0.000006919491,0.00002845199,0.000100514],"genre_scores_gemma":[0.9364289,0.000005666302,0.06294622,0.0003217995,0.0002407821,0.000002817467,0.00001164452,0.000006864218,0.00003526978],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9251509,"threshold_uncertainty_score":0.3796202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01183902731274235,"score_gpt":0.3040157941124831,"score_spread":0.2921767667997408,"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."}}