{"id":"W4392902789","doi":"10.1109/icassp48485.2024.10447420","title":"Efficient Learned Image Compression with Selective Kernel Residual Module and Channel-Wise Causal Context Model","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Google","keywords":"Computer science; Residual; Decoding methods; Encoding (memory); Kernel (algebra); Data compression; Image compression; Context (archaeology); Distortion (music); Artificial intelligence; Compression (physics); Algorithm; Rate–distortion theory; Image (mathematics); Pattern recognition (psychology); Theoretical computer science; Image processing; Mathematics; Bandwidth (computing)","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":[0.0001938272,0.0002667301,0.0002431843,0.0001826929,0.0002019352,0.0003172045,0.0005562034,0.00007904389,0.00000975955],"category_scores_gemma":[0.00002466029,0.0001860509,0.00002996242,0.0003633058,0.0001420652,0.0006160709,0.0008441365,0.0003247575,0.00002292669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006047937,"about_ca_system_score_gemma":0.00009919619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006329505,"about_ca_topic_score_gemma":0.00001419678,"domain_scores_codex":[0.9980152,0.00007549902,0.0002206227,0.0009162765,0.0004056532,0.0003667461],"domain_scores_gemma":[0.9988796,0.0001346694,0.00005650446,0.0006276339,0.0001363489,0.0001653131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007863527,0.001014486,0.00006911744,0.0004781752,0.0002518329,0.000856603,0.01158968,0.2461378,0.1864976,0.2422552,0.1264215,0.1836417],"study_design_scores_gemma":[0.000302009,0.0001594295,0.00004016678,0.0002180382,0.000006916136,0.00004438867,0.0000486455,0.9204804,0.07050141,0.007672718,0.000256719,0.0002691838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01378046,0.0006569421,0.9818307,0.0006082606,0.00007194787,0.0003673686,0.00002412109,0.001488595,0.001171603],"genre_scores_gemma":[0.805515,0.00003273953,0.1932239,0.0001763755,0.00002888624,0.00005363306,0.000007446423,0.00002731404,0.0009347788],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7917345,"threshold_uncertainty_score":0.7586937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01848326567702807,"score_gpt":0.2827288535105807,"score_spread":0.2642455878335526,"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."}}