{"id":"W3136191271","doi":"10.48550/arxiv.2103.08852","title":"Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Lidar; Segmentation; Benchmark (surveying); Encoder; Artificial intelligence; Point cloud; Convolutional neural network; Computer vision; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001370394,0.0003710641,0.0003460919,0.0002668939,0.0004407267,0.0002768147,0.001337108,0.0002422387,0.00002583803],"category_scores_gemma":[0.0000283365,0.0004908842,0.0002508265,0.001453459,0.0001390107,0.0007908639,0.002069463,0.0006596255,0.00007429111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005270976,"about_ca_system_score_gemma":0.0003509687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008879494,"about_ca_topic_score_gemma":0.0000454986,"domain_scores_codex":[0.9974283,0.0002069284,0.0003143554,0.001446135,0.000134997,0.0004692737],"domain_scores_gemma":[0.9972787,0.0001645271,0.0003616008,0.001661614,0.0003175234,0.0002160497],"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":[0.00001589011,0.00022339,0.003293787,0.0001427376,0.0001873602,0.00059737,0.0007428545,0.9084172,0.006106115,0.07879841,0.0001325819,0.001342282],"study_design_scores_gemma":[0.0003901568,0.00002239073,0.001442996,0.0001836939,0.0001627465,0.00003608985,0.0001545471,0.9761074,0.001321777,0.01928556,0.0002612695,0.0006314344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3884672,0.0002549057,0.6101523,0.0001052184,0.0003223817,0.0003350116,0.00001140471,0.0002422289,0.0001093923],"genre_scores_gemma":[0.9646292,0.0005003085,0.0338589,0.000170818,0.00009863517,0.000004592498,0.00006569233,0.00002895392,0.0006428934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5762934,"threshold_uncertainty_score":0.9997543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0935573175115638,"score_gpt":0.2267074236904283,"score_spread":0.1331501061788645,"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."}}