{"id":"W2966306124","doi":"10.1109/crv.2019.00019","title":"Active Vision in the Era of Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Ambiguity; Computer science; Artificial intelligence; Convolutional neural network; Object (grammar); Active vision; Cognitive neuroscience of visual object recognition; Set (abstract data type); Machine learning; Deep learning; Object detection; Artificial neural network; Active learning (machine learning); Computer vision; Pattern recognition (psychology)","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":[0.0001158244,0.00004651795,0.00006362922,0.00001421673,0.000008501343,0.000004884008,0.0001233105,0.00005219986,0.00007290022],"category_scores_gemma":[0.000010023,0.00003102575,0.00005436642,0.00006709305,0.00003184877,0.000002280311,0.00004868688,0.00007605621,0.000002488766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003766598,"about_ca_system_score_gemma":0.000008756653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004560287,"about_ca_topic_score_gemma":0.00004506747,"domain_scores_codex":[0.9996087,0.00004422329,0.0000924822,0.0001162756,0.00006604956,0.00007227177],"domain_scores_gemma":[0.9997097,0.00001376883,0.00003397114,0.0001989959,0.00003573492,0.000007808624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001247316,0.0001412091,0.01969142,0.000005609955,0.00004029387,0.000001601823,0.00004939797,0.001354243,0.959685,0.0003963699,0.008769231,0.009740931],"study_design_scores_gemma":[0.0008633723,0.0007157393,0.1271484,0.00001636042,0.00002995019,0.00001411745,0.0003488086,0.06808053,0.7937392,0.00022612,0.008529316,0.0002881194],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898803,0.0001186783,0.002534461,0.0001278307,0.000009588329,0.0001128814,6.211627e-7,0.000003755422,0.007211898],"genre_scores_gemma":[0.9990923,0.00003516817,0.000173113,0.0003699106,0.00002861785,0.000004151814,0.00004473592,0.000003255488,0.0002486915],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1659458,"threshold_uncertainty_score":0.1265193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003664767260230393,"score_gpt":0.2550873246561697,"score_spread":0.2514225573959393,"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."}}