{"id":"W4390480875","doi":"10.1109/tpami.2023.3348486","title":"Deep Lossy Plus Residual Coding for Lossless and Near-Lossless Image Compression","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Lossless compression; Lossy compression; Computer science; Lossless JPEG; Image compression; Context-adaptive binary arithmetic coding; Adaptive coding; Data compression; Context-adaptive variable-length coding; Entropy encoding; Algorithm; Tunstall coding; Artificial intelligence; Theoretical computer science; Image processing; Image (mathematics)","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":[0.0002882348,0.0003007927,0.0004078467,0.0004781488,0.0004473844,0.000746231,0.0005677052,0.00009396106,0.00004980221],"category_scores_gemma":[0.000007357547,0.0002519891,0.0001809664,0.0007785519,0.0001749658,0.0007269899,0.00003516032,0.0003488941,0.00000907202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000048182,"about_ca_system_score_gemma":0.00002954342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002517275,"about_ca_topic_score_gemma":0.0002496334,"domain_scores_codex":[0.9979774,0.00008526594,0.0004381818,0.0008987261,0.0002941204,0.0003062421],"domain_scores_gemma":[0.9985732,0.0004629152,0.00008818116,0.0006198694,0.0000914809,0.0001643698],"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":[0.00003304562,0.0000756744,0.0000373634,0.0001606193,0.0002810686,0.0000348824,0.0005230712,0.008722333,0.002909968,0.0007234599,0.00007414611,0.9864244],"study_design_scores_gemma":[0.00009433612,0.00008906527,0.00007669886,0.0001547588,0.0002215623,0.00002163243,0.000033712,0.8095044,0.1878669,0.001328407,0.0003270123,0.0002814953],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001317737,0.0007203815,0.9964654,0.0004563694,0.0002262067,0.0002768841,0.000154304,0.0003555877,0.00002716284],"genre_scores_gemma":[0.9511163,0.0007478574,0.04769909,0.00018575,0.00003005908,0.00007650255,0.00001812337,0.00002308737,0.0001032421],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9861429,"threshold_uncertainty_score":0.9999932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02382775102872816,"score_gpt":0.3132677874961801,"score_spread":0.289440036467452,"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."}}