{"id":"W4402667871","doi":"10.1016/j.isprsjprs.2024.09.006","title":"Weather-aware autopilot: Domain generalization for point cloud semantic segmentation in diverse weather scenarios","year":2024,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generalization; Autopilot; Segmentation; Domain (mathematical analysis); Point cloud; Computer science; Meteorology; Point (geometry); Environmental science; Artificial intelligence; Geography; Mathematics; Engineering; Aerospace 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":[],"consensus_categories":[],"category_scores_codex":[0.0004414065,0.0001463615,0.0002387201,0.0004013498,0.00006961328,0.0001172552,0.00004379176,0.00008552687,0.000006488467],"category_scores_gemma":[0.00001634634,0.0001253288,0.0001504793,0.0003339185,0.00002058066,0.0001299734,0.000010577,0.0001924697,0.000001336992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001102367,"about_ca_system_score_gemma":0.00001792371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000183388,"about_ca_topic_score_gemma":0.0001199633,"domain_scores_codex":[0.9991014,0.00004391859,0.0003826011,0.0001329803,0.0001466091,0.0001925127],"domain_scores_gemma":[0.999683,0.00005408955,0.00006190819,0.00007184714,0.0000615049,0.00006761423],"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":[0.00005756839,0.00002827204,0.0001228181,0.0005976156,0.000371882,0.0002478406,0.004689808,0.2157339,0.08899729,0.00002892003,0.000231259,0.6888928],"study_design_scores_gemma":[0.0004741397,0.00005135756,0.00001562552,0.0006551133,0.0001214902,0.0001411366,0.001090234,0.9905753,0.005151615,0.001138498,0.000432347,0.0001531036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3949077,0.001061471,0.6034071,0.00007752614,0.0004128069,0.00007550666,0.000002450953,0.00003738124,0.00001812185],"genre_scores_gemma":[0.9773003,0.000476267,0.02179347,0.00004614456,0.000304994,6.597057e-8,0.000005894457,0.00003467047,0.00003816782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7748414,"threshold_uncertainty_score":0.5110759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0121678505336735,"score_gpt":0.2483972998822916,"score_spread":0.2362294493486181,"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."}}