{"id":"W3189946487","doi":"10.1155/2021/7544355","title":"RS-Lane: A Robust Lane Detection Method Based on ResNeSt and Self-Attention Distillation for Challenging Traffic Situations","year":2021,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Guangzhou Municipal Science and Technology Project; Guangzhou Science and Technology Program key projects; Shenzhen Fundamental Research Program; Natural Science Foundation of Guangdong Province","keywords":"Computer science; Artificial intelligence; Segmentation; Feature (linguistics); Computer vision; Shadow (psychology); Inference; Representation (politics); Line (geometry); Advanced driver assistance systems; Feature extraction; Pattern recognition (psychology); Real-time computing; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000510922,0.001579383,0.001135247,0.002207481,0.0005163818,0.0009157198,0.002676878,0.001188243,0.002879879],"category_scores_gemma":[0.001271347,0.0005770857,0.001239576,0.000897306,0.0004500081,0.002001893,0.001248961,0.001441267,0.001797689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005444138,"about_ca_system_score_gemma":0.001139727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009166534,"about_ca_topic_score_gemma":0.01716307,"domain_scores_codex":[0.9994931,0.00005506611,0.0000205478,0.0002360151,0.00009966402,0.00009562163],"domain_scores_gemma":[0.9995484,0.00008519125,0.00005076916,0.0001075874,0.0001612871,0.00004677962],"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":[0.0005819687,0.000722474,0.006428308,0.0002459794,0.0002940778,0.0002921791,0.0002461777,0.07678755,0.04335524,0.002368578,0.02145136,0.8472261],"study_design_scores_gemma":[0.00005565715,0.0001596285,0.001922854,0.0000177914,0.00005419743,0.0001630089,0.00007818867,0.972432,0.01721437,0.002379104,0.005481904,0.00004132003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1299502,0.001193573,0.8266871,0.0004225165,0.0003668315,0.0003204499,0.001785251,0.03496721,0.004306941],"genre_scores_gemma":[0.5570694,0.0003624639,0.4226845,0.0006046347,0.0001698926,0.0002547409,0.009052455,0.001649101,0.008152844],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009166534,"threshold_uncertainty_score":0.01822639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007753830313121349,"score_gpt":0.2324021715527679,"score_spread":0.2246483412396466,"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."}}