{"id":"W2951341166","doi":"10.48550/arxiv.1502.04275","title":"segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Nvidia","keywords":"Segmentation; Artificial intelligence; Pascal (unit); Computer science; Inference; Convolutional neural network; Object detection; Markov random field; Pattern recognition (psychology); Exploit; Object (grammar); Context (archaeology); Image segmentation; Computer vision; Geography","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002103751,0.0002335904,0.0002385507,0.0001826994,0.0001552446,0.00009310859,0.0005265371,0.0001794781,9.127689e-7],"category_scores_gemma":[0.00003160736,0.0002943497,0.00007171326,0.0004974831,0.00005749093,0.0005513142,0.0007018149,0.0003880909,0.000002228413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002749766,"about_ca_system_score_gemma":0.00003189027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006033713,"about_ca_topic_score_gemma":0.0004816591,"domain_scores_codex":[0.9984313,0.00009918348,0.00021241,0.0008913214,0.00005499231,0.0003108474],"domain_scores_gemma":[0.9987869,0.0002158651,0.0002577929,0.0004802754,0.0001383341,0.0001207978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003353614,0.00002036156,0.0007034516,0.00002246591,0.00001221804,0.00001400176,0.0002329371,0.9332398,0.00005938016,0.007402998,0.00001202573,0.05824687],"study_design_scores_gemma":[0.0006148921,0.00004927886,0.0003383542,0.00002322867,0.00001985062,0.000005444003,0.000224783,0.9728853,0.0001403384,0.02539757,0.00003342591,0.000267542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1786,0.0001881237,0.8199801,0.00004569228,0.0002638825,0.0007123654,0.00000299471,0.0001478694,0.00005897091],"genre_scores_gemma":[0.9952551,0.0001020963,0.004335058,0.0000992706,0.0001010775,0.00002395481,0.00002020731,0.00001855808,0.00004465786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8166551,"threshold_uncertainty_score":0.9999509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07836379713199872,"score_gpt":0.2190607252072207,"score_spread":0.140696928075222,"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."}}