{"id":"W4318147859","doi":"10.1109/bigdata55660.2022.10020507","title":"Discovering Limitations of Image Quality Assessments with Noised Deep Learning Image Sets","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Google","keywords":"MNIST database; Computer science; Artificial intelligence; Pixel; Image quality; Image (mathematics); Image processing; Computer vision; Noise (video); Image resolution; Image restoration; Pattern recognition (psychology); Deep learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001708834,0.0002800979,0.0003340147,0.0002663892,0.0004244745,0.0006616238,0.007555006,0.00003599521,0.0001943694],"category_scores_gemma":[0.0003773488,0.0002802954,0.00005151549,0.0004631789,0.0001328138,0.00318961,0.00565855,0.000684987,0.00004011433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001868744,"about_ca_system_score_gemma":0.0005191971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005126414,"about_ca_topic_score_gemma":0.0004609226,"domain_scores_codex":[0.9951586,0.0006270029,0.0006757426,0.001240265,0.001939431,0.0003589812],"domain_scores_gemma":[0.9953462,0.000490205,0.0006270287,0.003095068,0.0003276853,0.0001138167],"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":[0.0007710004,0.003498412,0.003557518,0.0002267424,0.001278912,0.000470557,0.003147541,0.002604074,0.09501731,0.1025117,0.01520099,0.7717152],"study_design_scores_gemma":[0.004741988,0.001411669,0.0197345,0.0002592205,0.0001337163,0.00008530421,0.007551903,0.9013361,0.00573751,0.002996583,0.05407296,0.001938549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02227743,0.00002083648,0.9558966,0.002665506,0.002346364,0.0003727822,0.008451953,0.0001286014,0.007839932],"genre_scores_gemma":[0.9541134,0.000116059,0.02909539,0.0004225354,0.0001828301,0.00007570186,0.0155695,0.0000263162,0.0003982989],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9318359,"threshold_uncertainty_score":0.9999649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4654309621175568,"score_gpt":0.4333924151649992,"score_spread":0.03203854695255764,"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."}}