{"id":"W3161607120","doi":"10.1109/icpr48806.2021.9412906","title":"Foreground-focused domain adaption for object detection","year":2021,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Pipeline (software); Domain (mathematical analysis); Cityscape; Object detection; Benchmark (surveying); Object (grammar); Computer vision; Backpropagation; Inference; Domain adaptation; Pattern recognition (psychology); Adaptation (eye); Deep learning; Artificial neural network; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002990667,0.00008805986,0.00009582622,0.00006788369,0.0002007457,0.0002304811,0.0001819564,0.00005471419,0.00005447447],"category_scores_gemma":[0.00007772098,0.00008500618,0.00009000205,0.0003351144,0.00001316949,0.0004467401,0.00005423936,0.000073823,0.00005518567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005555529,"about_ca_system_score_gemma":0.00006886424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001106412,"about_ca_topic_score_gemma":0.0001316941,"domain_scores_codex":[0.9990851,0.00006711165,0.0001610305,0.0003071702,0.000175366,0.0002042627],"domain_scores_gemma":[0.9993629,0.0001219469,0.00005215087,0.0002692412,0.0001313235,0.00006244332],"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":[0.00002620083,0.00005760144,0.00005856679,0.00001785033,0.00002473898,0.00001021833,0.0009180157,0.0003200168,0.031257,0.3320332,0.0005307709,0.6347458],"study_design_scores_gemma":[0.003006022,0.0003500689,0.003423155,0.00002641513,0.00001387211,0.0000961988,0.001128546,0.5933653,0.06256607,0.08958387,0.2458351,0.0006054027],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00596072,0.00004255614,0.982851,0.0005930139,0.0004101019,0.0001495542,4.82838e-7,0.000261829,0.009730702],"genre_scores_gemma":[0.6577168,0.000004182331,0.3381076,0.0005142835,0.00008201183,0.00004174321,0.000005208104,0.000009128588,0.003519048],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.651756,"threshold_uncertainty_score":0.3466451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02622179823660913,"score_gpt":0.2525380406596637,"score_spread":0.2263162424230546,"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."}}