{"id":"W3180854701","doi":"10.3390/e23070881","title":"Compression Helps Deep Learning in Image Classification","year":2021,"lang":"en","type":"article","venue":"Entropy","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"JPEG; Artificial intelligence; Computer science; Image compression; Pattern recognition (psychology); Image (mathematics); Set (abstract data type); Compression ratio; Rank (graph theory); Artificial neural network; Compression (physics); JPEG 2000; Image processing; Mathematics","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":[0.0001133466,0.00007804939,0.00009473316,0.00006501944,0.00008037587,0.0001353731,0.0003338948,0.00003557103,0.00001782885],"category_scores_gemma":[0.0001694595,0.00007966969,0.00002274826,0.0003442099,0.00002647195,0.0006470352,0.000211317,0.0002162068,0.00004057718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006374678,"about_ca_system_score_gemma":0.00003792036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002211216,"about_ca_topic_score_gemma":0.000001728601,"domain_scores_codex":[0.9991124,0.00009865144,0.0001511572,0.0003035375,0.0001546704,0.0001795362],"domain_scores_gemma":[0.9994531,0.00004677312,0.00007398952,0.0003026017,0.00008759714,0.00003591228],"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":[0.000003806832,0.000072604,0.002050676,0.00001639476,0.000001699588,0.00007583003,0.0004066706,0.00004711673,0.8658329,0.02286979,0.0002212785,0.1084013],"study_design_scores_gemma":[0.0003789462,0.00002971035,0.01135044,0.0001059443,0.000001927787,0.00002713033,0.00009330473,0.6847175,0.2654391,0.02923123,0.008388504,0.000236292],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002700461,0.0004167232,0.9941124,0.0009516035,0.00007535269,0.00004692952,1.058529e-7,0.0004324401,0.001264013],"genre_scores_gemma":[0.3484582,0.00004632712,0.6511547,0.0001051274,0.00002233164,0.00001126276,0.000003722993,0.000006716024,0.0001916514],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6846703,"threshold_uncertainty_score":0.3248836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01486745926405595,"score_gpt":0.2865191307496002,"score_spread":0.2716516714855443,"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."}}