{"id":"W3183613752","doi":"10.1109/iccv48922.2021.01514","title":"Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation","year":2021,"lang":"en","type":"preprint","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; National Research Foundation of Korea; National Research Foundation","keywords":"Softmax function; Segmentation; Computer science; Inference; Artificial intelligence; Margin (machine learning); Machine learning; Pattern recognition (psychology); Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001987554,0.002849967,0.001380073,0.003271081,0.0009193097,0.00209102,0.003920415,0.002283824,0.008375114],"category_scores_gemma":[0.004882488,0.001097933,0.001919821,0.002592916,0.001375842,0.003336041,0.003842544,0.002780073,0.004646358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001642935,"about_ca_system_score_gemma":0.002287327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0117865,"about_ca_topic_score_gemma":0.02559493,"domain_scores_codex":[0.9987152,0.0001835505,0.00008299702,0.0005020528,0.0003245522,0.0001916789],"domain_scores_gemma":[0.9991226,0.0002818252,0.0001056904,0.0002015565,0.0002175765,0.00007086926],"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":[0.0006956561,0.0003651128,0.008642348,0.0003986115,0.0003642834,0.0004420392,0.0003587375,0.1861248,0.01884434,0.008419042,0.0474357,0.7279094],"study_design_scores_gemma":[0.00005393588,0.00005375826,0.002158297,0.00004229485,0.00004521101,0.0001750968,0.000114877,0.9667218,0.008311728,0.01452977,0.007741337,0.00005181381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03458795,0.0007566357,0.9117901,0.0006446211,0.0002086507,0.0003120027,0.002580418,0.04517956,0.003940112],"genre_scores_gemma":[0.3537931,0.0006242795,0.6165463,0.001198729,0.0002260482,0.0005578307,0.01207536,0.005512659,0.009465693],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0117865,"threshold_uncertainty_score":0.02801752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03221423061138843,"score_gpt":0.3137480837088291,"score_spread":0.2815338530974407,"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."}}