{"id":"W2945305363","doi":"10.48550/arxiv.1905.07542","title":"Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Consistency (knowledge bases); Monocular; Ground truth; Lidar; Artificial neural network; Deep learning; Depth map; Training (meteorology); Computer vision; Image (mathematics); Supervised learning; Point cloud; Point (geometry); Pattern recognition (psychology); Mathematics; Remote sensing; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001541539,0.00041341,0.0004284283,0.0002005036,0.0003013649,0.0002107201,0.001261451,0.0001823701,0.00002866365],"category_scores_gemma":[0.00001719379,0.0004137736,0.0001731525,0.0005288548,0.0001170516,0.001019156,0.001260361,0.0005780784,0.00004798609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002131235,"about_ca_system_score_gemma":0.0001955177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000485757,"about_ca_topic_score_gemma":0.00002465914,"domain_scores_codex":[0.9977483,0.0001494181,0.0002429696,0.001205351,0.0001526412,0.0005013324],"domain_scores_gemma":[0.997835,0.00008593991,0.0003121753,0.00137558,0.0002054687,0.0001858835],"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":[0.00002093692,0.00002536404,0.00547232,0.0000524617,0.00004466792,0.0002228279,0.0001065159,0.9859272,0.00002126124,0.004581335,0.00001750534,0.003507638],"study_design_scores_gemma":[0.0005584968,0.00003985634,0.0009257729,0.0002167187,0.00007481642,0.00003489425,0.0000373447,0.9899498,0.0000581419,0.007493118,0.00007918134,0.000531813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07462221,0.0001803827,0.9225902,0.00005338195,0.0005414799,0.0003796758,0.000001865099,0.0002621977,0.001368601],"genre_scores_gemma":[0.8400605,0.00003498769,0.1593799,0.0002091844,0.00005286217,3.252429e-7,0.00001454435,0.00002715572,0.0002205549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7654383,"threshold_uncertainty_score":0.9998314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05158376797996852,"score_gpt":0.2057092843045992,"score_spread":0.1541255163246307,"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."}}