{"id":"W4401878737","doi":"10.1109/tip.2024.3445737","title":"Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Alliance for Accessible Golf; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Decoding methods; Computer science; Entropy (arrow of time); Entropy encoding; Residual; Context model; Artificial intelligence; Image compression; Data compression; Cross entropy; Algorithm; Checkerboard; Context (archaeology); Image processing; Pattern recognition (psychology); Image (mathematics); 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":[0.0003391202,0.0009013608,0.0006272215,0.0004679552,0.0002725103,0.0004986034,0.001403734,0.000754258,0.00190568],"category_scores_gemma":[0.001148638,0.0002793891,0.0004142727,0.0006490679,0.0004267183,0.001662198,0.001187778,0.001439991,0.00068818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004968333,"about_ca_system_score_gemma":0.0008739821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004076933,"about_ca_topic_score_gemma":0.006097143,"domain_scores_codex":[0.9997545,0.0000284381,0.00001306111,0.0000675337,0.0001035606,0.00003287408],"domain_scores_gemma":[0.9997438,0.00006807069,0.00002718534,0.00007636581,0.00006417902,0.00002041626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003215661,0.0001994592,0.0009621248,0.0001546766,0.0000795111,0.0002805826,0.0001124939,0.2300534,0.06402908,0.02761078,0.00713197,0.6690643],"study_design_scores_gemma":[0.00001295437,0.00003419341,0.000152948,0.000006603949,0.00001065595,0.00006237475,0.000005822276,0.971462,0.02425282,0.002651064,0.001337459,0.00001107811],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02930166,0.0005664114,0.9645341,0.0002745436,0.00006322721,0.00005224352,0.0001336023,0.00245932,0.002614934],"genre_scores_gemma":[0.4289351,0.0006831919,0.5606906,0.0004024024,0.0001058337,0.000152647,0.0008501296,0.0002335408,0.007946609],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004076933,"threshold_uncertainty_score":0.008106411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01487410032970484,"score_gpt":0.2683706354828204,"score_spread":0.2534965351531156,"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."}}