{"id":"W2464204616","doi":"10.1109/cvpr.2016.393","title":"HD Maps: Fine-Grained Road Segmentation by Parsing Ground and Aerial Images","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":151,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Ground truth; Segmentation; Inertial measurement unit; Aerial imagery; Aerial survey; Parsing; Inference; Drone; Image segmentation; Remote sensing; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.00008575452,0.00006890785,0.00005936342,0.00000991447,0.0001119564,0.00004094998,0.00004457346,0.00002692083,0.0004542166],"category_scores_gemma":[0.0000119446,0.00004573873,0.00001458222,0.00005668673,0.0001238323,0.0001483557,0.00003576225,0.0000199556,0.000222322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004794002,"about_ca_system_score_gemma":0.000002280085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000618545,"about_ca_topic_score_gemma":0.00006851847,"domain_scores_codex":[0.9994541,0.00002200506,0.00009865308,0.0001913639,0.0001079662,0.0001259405],"domain_scores_gemma":[0.9997655,0.00002959982,0.0000311028,0.0001160728,0.000002792324,0.00005496561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005733738,0.00001499228,0.0007846425,9.740044e-7,0.000002627344,2.813885e-7,0.00008671858,0.000001347679,0.7113054,0.00003926165,0.03215928,0.2555988],"study_design_scores_gemma":[0.004800642,0.0002877099,0.213882,0.00008410029,0.00008326689,0.00007984303,0.000906118,0.001055007,0.582545,0.01106683,0.1838495,0.001360043],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9547716,0.0000251702,0.01550179,0.003302831,0.00007573534,0.0001760578,0.00001489428,0.00007661733,0.02605529],"genre_scores_gemma":[0.9865451,0.00002371171,0.006481987,0.0001361685,0.00004811268,0.0000020347,0.00001250206,0.000008005864,0.006742367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2542388,"threshold_uncertainty_score":0.4973353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007614698424362755,"score_gpt":0.2257034413586504,"score_spread":0.2180887429342877,"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."}}