{"id":"W2773584821","doi":"10.1609/aaai.v32i1.12323","title":"Co-Domain Embedding Using Deep Quadruplet Networks for Unseen Traffic Sign Recognition","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Samsung","keywords":"Computer science; Embedding; Artificial intelligence; Generalization; Traffic sign recognition; Pairwise comparison; Similarity (geometry); Feature (linguistics); Pattern recognition (psychology); Class (philosophy); Domain (mathematical analysis); Sign (mathematics); Synthetic data; Machine learning; Traffic sign; Image (mathematics); Mathematics","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":[0.0004030347,0.0002621716,0.0002710369,0.0001186815,0.0002732086,0.0001262666,0.0004687843,0.0001501056,0.00006421981],"category_scores_gemma":[0.0001435144,0.0002204168,0.0001248446,0.0003147042,0.0002428875,0.0002207754,0.00003111386,0.0002643608,0.00002060398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009950539,"about_ca_system_score_gemma":0.00002766541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007586098,"about_ca_topic_score_gemma":0.000009868051,"domain_scores_codex":[0.9984887,0.000008786858,0.0004906349,0.0002980552,0.0002200629,0.0004937714],"domain_scores_gemma":[0.9989994,0.00008084713,0.0001832814,0.0001371149,0.0005275436,0.00007177363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005230281,0.00008627064,0.0001239741,0.0003265035,0.0001370646,9.450864e-7,0.006131667,0.1036805,0.4464661,0.03758932,0.0007264111,0.4042082],"study_design_scores_gemma":[0.00003848253,0.0001315756,0.00001487871,0.0002987407,0.00002482866,0.000004291061,0.001373448,0.5712137,0.4078186,0.01871717,0.0001211721,0.0002432261],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7963287,0.00002314245,0.1986064,0.00007507866,0.001356846,0.0006333815,0.00001328795,0.0001740885,0.002789064],"genre_scores_gemma":[0.9920231,0.00002017443,0.006909479,0.00005021714,0.0008949339,0.00003680792,0.000002975431,0.0000455212,0.00001682267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4675331,"threshold_uncertainty_score":0.8988335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05853266592608864,"score_gpt":0.2991962923570157,"score_spread":0.2406636264309271,"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."}}