{"id":"W3014073509","doi":"10.48550/arxiv.2003.12943","title":"Adaptive Object Detection with Dual Multi-Label Prediction","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Artificial intelligence; Regularization (linguistics); Pattern recognition (psychology); Object detection; Benchmark (surveying); Object (grammar); Cognitive neuroscience of visual object recognition; Feature (linguistics); Machine learning; Computer vision","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":[0.001100919,0.001106992,0.001431589,0.0006676227,0.000345014,0.0009396174,0.003411905,0.001644735,0.001511779],"category_scores_gemma":[0.002160183,0.0004650679,0.0009289887,0.0007504745,0.0008884959,0.002051264,0.001888218,0.002779312,0.001370486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006717088,"about_ca_system_score_gemma":0.0007264761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002784292,"about_ca_topic_score_gemma":0.003397565,"domain_scores_codex":[0.9990644,0.0001629902,0.00002354741,0.000433329,0.0002093427,0.0001063324],"domain_scores_gemma":[0.9989129,0.0003719562,0.0001057042,0.0003158449,0.0002181976,0.00007533597],"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":[0.0004888358,0.0006199083,0.003858062,0.0001716706,0.0002108466,0.0003142951,0.0001678616,0.2967323,0.03519222,0.008744843,0.008590486,0.6449087],"study_design_scores_gemma":[0.000006502181,0.00003491062,0.000321865,0.000004571061,0.00001119295,0.00004919653,0.000009397545,0.9906577,0.004330319,0.003862231,0.0007031013,0.000009072332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0253674,0.0004786399,0.9700024,0.0002398618,0.00009901304,0.00005483728,0.0001217036,0.002465111,0.001171138],"genre_scores_gemma":[0.6536701,0.0004204368,0.3324876,0.0009403267,0.000172971,0.0001720513,0.001321365,0.0002463753,0.01056875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003411905,"threshold_uncertainty_score":0.005822241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1135052656683792,"score_gpt":0.1928038610361109,"score_spread":0.07929859536773165,"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."}}