{"id":"W4312102546","doi":"10.1109/tencon55691.2022.9977590","title":"Data Augmentation Methods for Low Resolution Facial Images","year":2022,"lang":"en","type":"article","venue":"TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Regularization (linguistics); Pattern recognition (psychology); Face (sociological concept); Set (abstract data type); Data set; Training set; Resolution (logic); Image resolution; Machine learning; Data mining; 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","sts"],"consensus_categories":[],"category_scores_codex":[0.002348412,0.0004859359,0.0005617146,0.0004893531,0.001305216,0.0004243537,0.004707818,0.0001315309,0.0004732704],"category_scores_gemma":[0.0005499344,0.0005326081,0.000164089,0.001183861,0.0002922594,0.003286749,0.002250555,0.0006992021,0.00003221349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000480857,"about_ca_system_score_gemma":0.0007967002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006643703,"about_ca_topic_score_gemma":0.00001577462,"domain_scores_codex":[0.994848,0.0008458544,0.0008176222,0.001874045,0.0008078286,0.0008066905],"domain_scores_gemma":[0.9956418,0.000461801,0.0007812232,0.002432764,0.0004864763,0.0001959045],"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":[0.00026232,0.0003293836,0.000050571,0.0001827522,0.0000771457,0.0000671436,0.001156133,0.000276108,0.1115565,0.009692062,0.1137151,0.7626348],"study_design_scores_gemma":[0.001579924,0.0008162648,0.00008568735,0.00009208843,0.00008020843,0.0002028765,0.001064975,0.7537446,0.02579105,0.07205579,0.1431516,0.001334947],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002040452,0.0005793875,0.991354,0.002970735,0.001455274,0.00117875,0.0002433062,0.001119073,0.0008953746],"genre_scores_gemma":[0.02495218,0.0003359017,0.9650124,0.001044783,0.0002683184,0.001722454,0.0006683733,0.00008217183,0.005913371],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7612999,"threshold_uncertainty_score":0.9999949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1143844673576007,"score_gpt":0.4027301345308763,"score_spread":0.2883456671732756,"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."}}