{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001134745,0.001955917,0.001165784,0.001597889,0.0004820197,0.001063952,0.002797993,0.001764703,0.003165197],"category_scores_gemma":[0.002136718,0.000826961,0.0007593568,0.00115152,0.0005777635,0.00269163,0.002169976,0.001681131,0.001313753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000802496,"about_ca_system_score_gemma":0.001170684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00579495,"about_ca_topic_score_gemma":0.01474751,"domain_scores_codex":[0.9994715,0.00008240988,0.00001636232,0.000220316,0.0001351606,0.00007433131],"domain_scores_gemma":[0.9995702,0.0001515667,0.00004142128,0.0001166943,0.00008237646,0.00003778475],"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":[0.0005292502,0.0002689584,0.003360941,0.0002323314,0.0002368315,0.0002188229,0.00009279523,0.1132313,0.02154465,0.007935585,0.01449372,0.8378549],"study_design_scores_gemma":[0.00002702848,0.00009967144,0.0007681696,0.00002459275,0.00004464623,0.0001035091,0.00001767911,0.9688601,0.01273372,0.01199233,0.00531069,0.00001788468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05647853,0.003823622,0.9169901,0.0005186847,0.0003165669,0.000169348,0.00114065,0.01607124,0.004491239],"genre_scores_gemma":[0.3967255,0.001090193,0.5874923,0.0007956384,0.0002104769,0.0001943425,0.002885181,0.0006697784,0.009936498],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00579495,"threshold_uncertainty_score":0.01152241,"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."}}