{"id":"W4400314741","doi":"10.1109/jsait.2024.3422011","title":"JPEG Compliant Compression for DNN Vision","year":2024,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Information Theory","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; JPEG; Compression (physics); Computer vision; JPEG 2000; Artificial intelligence; Image compression; Data compression; Image processing; Materials science; Image (mathematics); Composite material","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":[0.001170613,0.000217122,0.0002273986,0.0008905982,0.0002525741,0.0006972417,0.0009548102,0.0001180703,0.00003948068],"category_scores_gemma":[0.0002750579,0.0001664823,0.00009084415,0.0008246368,0.00003777293,0.005230452,0.0001071306,0.0006602597,0.0001091269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002457967,"about_ca_system_score_gemma":0.0001591406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.305569e-7,"about_ca_topic_score_gemma":4.551511e-7,"domain_scores_codex":[0.9979931,0.0002110244,0.0007623964,0.0002138199,0.0004805463,0.0003391618],"domain_scores_gemma":[0.9979746,0.0008574832,0.0002680754,0.0004151599,0.0003489651,0.0001356909],"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":[0.0003653619,0.0001308718,0.00001251442,0.0001265935,0.00003160344,0.00003036381,0.001240831,0.004060506,0.004571709,0.3250408,0.08119724,0.5831916],"study_design_scores_gemma":[0.001278522,0.000734231,0.0005441282,0.002811317,0.00001094912,0.0005410403,0.00008553925,0.3794203,0.04392299,0.3078624,0.2621743,0.0006143124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001764907,0.0001703529,0.9937348,0.0004330736,0.001383489,0.0003888423,0.00002738539,0.0005990078,0.001498146],"genre_scores_gemma":[0.8453033,0.0003312356,0.1510263,0.00231964,0.000439232,0.0001510831,0.0001264254,0.00004824333,0.0002545552],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8435384,"threshold_uncertainty_score":0.678895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0126917201907885,"score_gpt":0.3050254443854841,"score_spread":0.2923337241946956,"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."}}