{"id":"W2946106399","doi":"10.1007/978-3-030-18305-9_55","title":"Compression Improves Image Classification Accuracy","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Image compression; Computer science; JPEG; Artificial intelligence; Compression (physics); Convolutional neural network; Compression ratio; Singular value decomposition; Pattern recognition (psychology); Texture compression; Data compression; Lossless compression; Data compression ratio; Image (mathematics); Computer vision; Image processing","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"],"consensus_categories":[],"category_scores_codex":[0.0004351885,0.0004078605,0.0003687948,0.0005879294,0.0002950183,0.0006075135,0.003121391,0.000321745,0.00002651522],"category_scores_gemma":[0.00005246955,0.0003671394,0.0001336876,0.0005183233,0.0004278266,0.0009158592,0.001154647,0.0007149489,0.0002011118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002448239,"about_ca_system_score_gemma":0.0004285333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001473898,"about_ca_topic_score_gemma":0.000007588222,"domain_scores_codex":[0.9969577,0.00002276899,0.000493755,0.001447519,0.0006458249,0.0004324484],"domain_scores_gemma":[0.9968641,0.000348332,0.0004441932,0.001946651,0.0002725029,0.0001242224],"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":[0.000002643173,0.0000272467,0.000009625947,0.00002772838,0.000004100457,0.000004775646,0.0001182179,0.0003782576,0.01677937,0.06387158,0.0001108746,0.9186656],"study_design_scores_gemma":[0.0002157042,0.0001774322,0.0006685608,0.0002754328,0.000008039424,0.00004439145,2.2275e-7,0.79223,0.02081404,0.1666563,0.01806064,0.000849297],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005676901,0.0001256349,0.9875107,0.001058394,0.0006979865,0.0006535532,0.000004687982,0.0004190346,0.009473172],"genre_scores_gemma":[0.2236897,0.0001327857,0.7725304,0.001287918,0.0004109464,0.00004740806,0.00001459712,0.00005186868,0.00183438],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9178163,"threshold_uncertainty_score":0.999878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01929280260973512,"score_gpt":0.2734313471444804,"score_spread":0.2541385445347453,"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."}}