{"id":"W4386597007","doi":"10.1109/icip49359.2023.10221982","title":"JPEG Compliant Compression for DNN Vision","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"JPEG; Computer science; Image compression; Artificial intelligence; Quantization (signal processing); Pixel; Lossless JPEG; JPEG 2000; Data compression; Data compression ratio; Artificial neural network; Compression ratio; Computer vision; Deep neural networks; Image processing; Image (mathematics); Engineering","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":[0.0007227148,0.001068307,0.0003305174,0.001203968,0.0003384324,0.0008309116,0.001134217,0.000780086,0.0128381],"category_scores_gemma":[0.002904689,0.0002527715,0.0004236749,0.001242938,0.0004046124,0.001193509,0.0006764937,0.001337854,0.004989168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007922023,"about_ca_system_score_gemma":0.0006592564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003705031,"about_ca_topic_score_gemma":0.005798031,"domain_scores_codex":[0.9994484,0.00005623167,0.00004821414,0.00009443914,0.0003173178,0.00003547708],"domain_scores_gemma":[0.9994356,0.0001122793,0.00003809006,0.0001746349,0.0002178305,0.00002148701],"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":[0.0003116266,0.0001008076,0.0007613794,0.0005090644,0.00008562783,0.0002582636,0.00008992961,0.03416404,0.07693306,0.03443994,0.05758481,0.7947615],"study_design_scores_gemma":[0.00009368268,0.0001661694,0.002083915,0.0001737507,0.00005462097,0.000946896,0.00005721456,0.5776531,0.2380845,0.03728136,0.1433324,0.00007250285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01158132,0.001677448,0.9633363,0.0004797904,0.0006693156,0.0002443285,0.002058698,0.007725062,0.01222774],"genre_scores_gemma":[0.1246993,0.001900353,0.8498783,0.0005493051,0.0001868499,0.0003203402,0.006004993,0.001395168,0.01506546],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0128381,"threshold_uncertainty_score":0.04294771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04797949755490941,"score_gpt":0.3473820569376926,"score_spread":0.2994025593827833,"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."}}