{"id":"W4307356725","doi":"10.20944/preprints202210.0418.v1","title":"An Adaptive Refinement Scheme for Depth Estimation Networks","year":2022,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Benchmark (surveying); Computer science; Inference; Generalization; Scheme (mathematics); Particle swarm optimization; Artificial intelligence; Segmentation; Function (biology); Algorithm; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008632204,0.0003432224,0.0003454631,0.0001629993,0.0003205008,0.00009307244,0.002023283,0.0001294268,0.0002832364],"category_scores_gemma":[0.0001702486,0.0003798228,0.0001786634,0.0002143131,0.00004045761,0.0005015468,0.004431208,0.0008021454,0.00007603809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002855244,"about_ca_system_score_gemma":0.0001630396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003464962,"about_ca_topic_score_gemma":0.000004890295,"domain_scores_codex":[0.9970375,0.0001420657,0.0004989801,0.001463723,0.0004229709,0.0004348066],"domain_scores_gemma":[0.996913,0.0000940627,0.0004206893,0.002162963,0.0002363191,0.0001730029],"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":[0.0001252934,0.0004315744,0.02192301,0.0001124648,0.0001183004,0.00001362815,0.001187824,0.7557446,0.001060832,0.02554365,0.0003998667,0.193339],"study_design_scores_gemma":[0.0003306905,0.00007131604,0.01433343,0.00006819231,0.00001326096,0.00000287787,0.00006224712,0.9694022,0.001326128,0.008280109,0.00569638,0.0004131881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008631891,0.0001141852,0.9856771,0.0005864682,0.001098862,0.0009939531,0.000009140934,0.0004845252,0.002403833],"genre_scores_gemma":[0.5305063,0.0000392529,0.4675294,0.0006140029,0.0001279647,0.0007162066,0.00009932533,0.00003508369,0.0003325292],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5218743,"threshold_uncertainty_score":0.9998654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.151857525712293,"score_gpt":0.402466417204075,"score_spread":0.250608891491782,"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."}}