{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001144573,0.0009807948,0.0005644974,0.0007808513,0.0003296083,0.001098061,0.0006432306,0.0009782778,0.002295106],"category_scores_gemma":[0.005748107,0.0002644316,0.0004286924,0.0008773337,0.0009328133,0.002103848,0.001007787,0.001636029,0.0008398151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008092349,"about_ca_system_score_gemma":0.000830034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004069417,"about_ca_topic_score_gemma":0.005173196,"domain_scores_codex":[0.9994577,0.0001131838,0.00003313914,0.0001194794,0.0001896572,0.00008688738],"domain_scores_gemma":[0.998562,0.0007441251,0.0001191579,0.0002847767,0.0002235597,0.00006631119],"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":[0.0009772141,0.0004079622,0.008221543,0.0003187487,0.0001039893,0.0004987922,0.0001856607,0.1879806,0.03898402,0.01787266,0.01115946,0.7332893],"study_design_scores_gemma":[0.00006290205,0.0004559022,0.00426694,0.00008709406,0.00005908453,0.0002901439,0.00009773365,0.9157706,0.04873414,0.02288246,0.007257289,0.00003576536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6246184,0.01251898,0.3298526,0.006066462,0.0007020819,0.000153495,0.0008528453,0.003641869,0.02159326],"genre_scores_gemma":[0.9162371,0.002880641,0.0726553,0.000719045,0.0002488757,0.00004368107,0.0007711865,0.000138204,0.006305886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004069417,"threshold_uncertainty_score":0.00809145,"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."}}