{"id":"W2982143932","doi":"10.1109/iccv.2019.00033","title":"What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance","year":2019,"lang":"en","type":"article","venue":"","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Color constancy; Artificial intelligence; Robustness (evolution); Deep neural networks; Deep learning; Artificial neural network; Color balance; Segmentation; Computer vision; Image segmentation; Pattern recognition (psychology); Image (mathematics); Image processing; Color image","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":[0.0003401884,0.0002656369,0.0002564683,0.000104517,0.0002682643,0.0005731089,0.0009083684,0.0000899347,0.0001893998],"category_scores_gemma":[0.00002617046,0.0002380373,0.00006907094,0.0004689259,0.00007477436,0.001839771,0.0003319008,0.0004127039,0.0002207614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001190983,"about_ca_system_score_gemma":0.00004392433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001182319,"about_ca_topic_score_gemma":0.00005959037,"domain_scores_codex":[0.9978988,0.0001180476,0.0002990813,0.0005717105,0.0004191886,0.0006932336],"domain_scores_gemma":[0.9988379,0.0001236394,0.000168751,0.00065917,0.0001028626,0.0001076404],"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":[0.0001157728,0.0001762704,0.02987388,0.0001229891,0.00005703456,0.00007071309,0.002576177,0.04368047,0.003412128,0.01482395,0.002537497,0.9025531],"study_design_scores_gemma":[0.000475688,0.0007944931,0.003250716,0.0002371674,0.000006908971,0.00001828856,0.0002151242,0.9745942,0.0172378,0.000209231,0.002429817,0.000530533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7583604,0.0003715848,0.2145676,0.0008343025,0.002286889,0.0008547896,2.20661e-7,0.001561303,0.02116294],"genre_scores_gemma":[0.967115,0.00007341215,0.02803662,0.001843792,0.00009980256,0.00004011019,0.000003344028,0.00002432164,0.002763594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9309137,"threshold_uncertainty_score":0.9706877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01532608444085527,"score_gpt":0.2524683634747277,"score_spread":0.2371422790338725,"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."}}