{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001793453,0.000310338,0.0002547976,0.0002519248,0.000638905,0.0007796497,0.0002924882,0.00009336873,0.000003620863],"category_scores_gemma":[0.000004440301,0.0002453747,0.00002405737,0.0004129129,0.0002347576,0.004777398,0.00002830896,0.0004485109,0.000006686439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006946394,"about_ca_system_score_gemma":0.0001310975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001777805,"about_ca_topic_score_gemma":0.00001089861,"domain_scores_codex":[0.9983445,0.00004319303,0.0003050106,0.0007405462,0.0002339761,0.0003327836],"domain_scores_gemma":[0.9991532,0.0000622108,0.00009602605,0.0003979554,0.0001599681,0.0001306193],"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":[0.0001239996,0.0000710925,0.000002842766,0.0005127648,0.00001521068,0.000006170932,0.0009107847,0.006469174,0.1074208,0.00008392356,0.00006786696,0.8843154],"study_design_scores_gemma":[0.0003702228,0.0001240847,0.00003330292,0.0007246099,0.00001865402,0.00003735451,0.00004053708,0.7463436,0.2515948,0.0004107893,0.00005482541,0.0002472188],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02679138,0.000915698,0.9705995,0.0001898036,0.00009304562,0.0003017421,0.000027856,0.0009078629,0.0001731033],"genre_scores_gemma":[0.7280291,0.0002079312,0.2713744,0.00002863489,0.00001925736,0.00006031354,0.000004680482,0.00003236968,0.0002432499],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8840682,"threshold_uncertainty_score":0.9999998,"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."}}