{"id":"W4212826194","doi":"10.1109/jiot.2022.3151374","title":"Lightweight Monocular Depth Estimation on Edge Devices","year":2022,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Encoder; Pruning; Enhanced Data Rates for GSM Evolution; Monocular; Upsampling; Computational complexity theory; Artificial intelligence; Computer engineering; Computer vision; Algorithm; Image (mathematics)","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":[0.0002616846,0.0007728206,0.0005517745,0.0005255192,0.000351317,0.0008030097,0.001441717,0.000654774,0.006474376],"category_scores_gemma":[0.001452052,0.0004361593,0.0003474003,0.0004881812,0.000261032,0.001962024,0.001453514,0.0007173301,0.001476407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005540031,"about_ca_system_score_gemma":0.0007132806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004435158,"about_ca_topic_score_gemma":0.008982054,"domain_scores_codex":[0.999527,0.00003870454,0.00001635315,0.0001075648,0.0002396135,0.00007079302],"domain_scores_gemma":[0.9995995,0.0001092976,0.00003255754,0.0001141212,0.0001224891,0.00002208589],"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":[0.001115139,0.0001413074,0.004757408,0.0002799872,0.0001101854,0.0005187595,0.0001845004,0.08935209,0.1464554,0.01553423,0.02077873,0.7207723],"study_design_scores_gemma":[0.00002675809,0.0001025241,0.001985121,0.00003333094,0.00002150434,0.000296103,0.00006669434,0.9049246,0.07699986,0.006230853,0.00928197,0.00003071934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04724943,0.0004444209,0.9360793,0.0002221565,0.00007818131,0.00008775737,0.0007449914,0.005402547,0.009691352],"genre_scores_gemma":[0.4419117,0.000384069,0.5477534,0.0003051279,0.00003953002,0.00009626305,0.00117244,0.000245064,0.008092425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006474376,"threshold_uncertainty_score":0.02165896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01743491516282089,"score_gpt":0.2813025027585311,"score_spread":0.2638675875957102,"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."}}