{"id":"W4399258645","doi":"10.1016/j.cviu.2024.104048","title":"Self-supervised monocular depth estimation with self-distillation and dense skip connection","year":2024,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Monocular; Connection (principal bundle); Artificial intelligence; Distillation; Computer science; Estimation; Computer vision; Pattern recognition (psychology); Mathematics; Chromatography; Chemistry; Geometry; Engineering","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002429143,0.0002235073,0.0001811506,0.0002823002,0.0003714936,0.001407797,0.0001239335,0.00005213577,0.000003944361],"category_scores_gemma":[0.000009756479,0.0001801126,0.00003593278,0.0004008456,0.00005427675,0.002117099,0.0001752795,0.0001553885,0.000008121069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001654232,"about_ca_system_score_gemma":0.00003376867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002332247,"about_ca_topic_score_gemma":0.000001400443,"domain_scores_codex":[0.9986339,0.00006780427,0.0002188459,0.0006063499,0.0002402557,0.0002328814],"domain_scores_gemma":[0.99936,0.0001538262,0.00005440648,0.0002307084,0.00005675827,0.0001442494],"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":[0.00005519771,0.0001047166,0.000340312,0.0006127837,0.0001249069,0.0002486742,0.005866551,0.0004818964,0.002317572,0.08895548,0.001022132,0.8998698],"study_design_scores_gemma":[0.0005888424,0.0002151383,0.0003459591,0.000253195,0.0000217226,0.0002588129,0.0001432206,0.9896879,0.0001871655,0.007162987,0.0008815099,0.0002536081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004147148,0.0005369239,0.9927355,0.0007119032,0.0002810716,0.0002310951,6.879394e-7,0.0009327951,0.0004228631],"genre_scores_gemma":[0.4510956,0.0001259856,0.5485719,0.0001345173,0.00004147082,0.000002257657,0.000004474385,0.00001445678,0.000009333326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.989206,"threshold_uncertainty_score":0.9996288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01843607504009122,"score_gpt":0.2702363480206209,"score_spread":0.2518002729805297,"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."}}