{"id":"W2964211168","doi":"10.1109/cvpr.2016.79","title":"Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":214,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov random field; Computer science; ENCODE; Artificial intelligence; Convolutional neural network; Conditional random field; Pattern recognition (psychology); Image segmentation; Segmentation; Heuristics; Markov chain; Inference; Pixel; Computer vision; Machine learning","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":[0.0001056595,0.0003305929,0.0002964216,0.0001092023,0.000216484,0.0001767237,0.001103497,0.0001525901,0.00001255389],"category_scores_gemma":[0.00002985944,0.0002500612,0.00007800494,0.0002343023,0.00006082291,0.0003812505,0.0006201532,0.000216616,0.0000247286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002430903,"about_ca_system_score_gemma":0.0002041596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004802376,"about_ca_topic_score_gemma":0.0001946869,"domain_scores_codex":[0.9979632,0.0000363184,0.000367464,0.0009927513,0.0002341409,0.0004060748],"domain_scores_gemma":[0.9977515,0.0004037023,0.0003845601,0.001040739,0.0002996945,0.0001198247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007442972,0.0001811638,0.0008948995,0.0001809926,0.0002519471,0.00001431548,0.00116238,0.02870874,0.008042134,0.5751411,0.002765361,0.3825825],"study_design_scores_gemma":[0.003433337,0.0003757674,0.005903746,0.0006071635,0.0001042407,0.00007559373,0.00008833165,0.6136701,0.03310577,0.3308465,0.009063947,0.002725531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004024491,0.00004987279,0.9902762,0.00154277,0.0003016895,0.001687117,0.00002219238,0.0007158295,0.001379847],"genre_scores_gemma":[0.2569625,0.00002280924,0.7401639,0.0003776581,0.0001379881,0.001248783,0.00004140396,0.00003705604,0.001007835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5849613,"threshold_uncertainty_score":0.9999952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03564884137849786,"score_gpt":0.2797257065967211,"score_spread":0.2440768652182232,"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."}}