{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003456051,0.0006362732,0.0007583801,0.0005338497,0.0001010706,0.0007975541,0.0006445562,0.0004007357,0.0001468167],"category_scores_gemma":[0.00006683829,0.0006599869,0.0003047463,0.0002405943,0.00004130299,0.0003178161,0.0003823309,0.0009139721,0.000008582058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001154031,"about_ca_system_score_gemma":0.0001486181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000957167,"about_ca_topic_score_gemma":0.00004309325,"domain_scores_codex":[0.996817,0.0001504066,0.0008122639,0.001008304,0.0007204648,0.0004915572],"domain_scores_gemma":[0.9982092,0.0001821515,0.0002613965,0.0004588127,0.000781989,0.0001064605],"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":[0.0008860476,0.0004223741,0.0008550344,0.001412386,0.001430188,0.0002172157,0.005174674,0.623013,0.06870279,0.001981748,0.01073749,0.2851671],"study_design_scores_gemma":[0.002549441,0.000170291,0.004100904,0.001961454,0.00005087448,0.00001114463,0.0007441078,0.957302,0.03003815,0.001754027,0.0003930278,0.0009245776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2058504,0.0001793929,0.7819192,0.0000680514,0.008888821,0.001483204,0.0003333436,0.0002155848,0.001061948],"genre_scores_gemma":[0.9398413,0.0001914632,0.05569702,0.0000743046,0.001189778,0.0005933423,0.002231176,0.00009293054,0.0000886754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7339909,"threshold_uncertainty_score":0.9995852,"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."}}