{"id":"W3165441654","doi":"10.1145/3460319.3464802","title":"Automatic test suite generation for key-points detection DNNs using many-objective search (experience paper)","year":2021,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation of Korea; Fonds National de la Recherche Luxembourg; National Research Foundation; European Commission","keywords":"Suite; Deep neural networks; Object detection; Artificial neural network; Pattern recognition (psychology); Feature extraction; Face detection; Deep learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001280021,0.0001235789,0.0001354702,0.00006963159,0.0002148169,0.00003394401,0.0000762343,0.000160113,0.0001845422],"category_scores_gemma":[0.00009021559,0.0001314705,0.00005007086,0.0002318016,0.00003945078,0.0002346577,0.00003301434,0.0001536409,0.00002525136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001870625,"about_ca_system_score_gemma":0.00003870132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001776714,"about_ca_topic_score_gemma":0.0001464559,"domain_scores_codex":[0.9992131,0.00002036558,0.0001992361,0.0002238989,0.00008521968,0.0002582023],"domain_scores_gemma":[0.9995715,0.00009869337,0.00001769738,0.0002034397,0.00007133729,0.00003731116],"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":[0.000002245218,0.00003613197,0.0009080641,0.00005629048,0.00003773955,0.000009005339,0.001452992,0.008562123,0.9419451,0.001403495,0.00001925434,0.04556755],"study_design_scores_gemma":[0.0001313814,0.00002142184,0.001524154,0.000006326208,0.000007318289,0.00002460119,0.0002689976,0.5962549,0.4014548,0.0001160679,0.00009021343,0.00009984998],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6761968,0.00004843053,0.3224186,0.00006276882,0.0001455478,0.0001764196,0.00000460962,0.0005605884,0.0003861961],"genre_scores_gemma":[0.9867103,0.00001571938,0.01288426,0.0000623883,0.00007741094,0.00005918419,0.000009095275,0.00002646875,0.000155207],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5876927,"threshold_uncertainty_score":0.5361212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02181499228368204,"score_gpt":0.2554304331397103,"score_spread":0.2336154408560282,"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."}}