{"id":"W3035197843","doi":"10.1109/icme46284.2020.9102877","title":"Learned Variable-Rate Image Compression With Residual Divisive Normalization","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Residual; Normalization (sociology); Image compression; Rounding; Algorithm; Codec; Artificial intelligence; MNIST database; Quantization (signal processing); Encoder; Decoding methods; Pattern recognition (psychology); Image processing; Deep learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006584611,0.000744777,0.0005434104,0.0004578849,0.0001755712,0.0005360878,0.001216816,0.000516478,0.001327695],"category_scores_gemma":[0.001536627,0.0002160891,0.0004162772,0.0005920003,0.0007059035,0.00108558,0.0008746831,0.001190149,0.0004091868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006039712,"about_ca_system_score_gemma":0.0007024629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002629642,"about_ca_topic_score_gemma":0.003391158,"domain_scores_codex":[0.999645,0.00005250129,0.00001751974,0.00008406212,0.0001681054,0.00003272198],"domain_scores_gemma":[0.999604,0.0001061413,0.00004337369,0.00009880561,0.0001316227,0.00001592822],"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":[0.0002070192,0.0001092079,0.0006105199,0.0001134478,0.0000664324,0.0001179399,0.00009392473,0.4428844,0.04462701,0.0180761,0.002845909,0.4902481],"study_design_scores_gemma":[0.000007684765,0.00002674792,0.0001277868,0.000007167484,0.000007552675,0.00005825665,0.00000622565,0.9790557,0.01703474,0.002541548,0.001117868,0.000008817266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02125916,0.000386414,0.9752,0.0001224405,0.00003956943,0.00004175552,0.00006141634,0.0009633583,0.001925878],"genre_scores_gemma":[0.5009891,0.0005060722,0.4895111,0.0002231873,0.00007247852,0.0001127384,0.0003968856,0.0002796206,0.007908884],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002629642,"threshold_uncertainty_score":0.005228639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02949102580317836,"score_gpt":0.2915910654463028,"score_spread":0.2621000396431244,"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."}}