{"id":"W4386310553","doi":"10.2139/ssrn.4557549","title":"Enhanced Residual Swinv2 Transformer for Learned Image Compression","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Residual; Transformer; Image compression; Computer science; Computer vision; Artificial intelligence; Environmental science; Image (mathematics); Electrical engineering; Image processing; Engineering; Algorithm; Voltage","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002633912,0.0006042523,0.0007127695,0.0004770474,0.0005964516,0.0004737241,0.004194438,0.0004752786,0.00001232724],"category_scores_gemma":[0.0002153234,0.0005373358,0.0004466311,0.000303447,0.0000929232,0.001003781,0.001182842,0.006389816,0.00005270498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009802409,"about_ca_system_score_gemma":0.00345762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003382214,"about_ca_topic_score_gemma":0.0001161884,"domain_scores_codex":[0.9932724,0.0002399262,0.0009155428,0.00120021,0.0008110238,0.003560926],"domain_scores_gemma":[0.9969723,0.0003063807,0.0007094059,0.001423095,0.0003801581,0.0002087084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005665823,0.0003623625,0.000008293029,0.0003739771,0.0006547867,0.00003755507,0.001077938,0.001463177,0.1467244,0.3193571,0.02029663,0.5090773],"study_design_scores_gemma":[0.0009060161,0.0003761252,0.0000191875,0.0004036545,0.00003837133,0.0000865695,0.0001273615,0.003475284,0.07282873,0.9169211,0.004150396,0.0006671945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009377848,0.001309472,0.9911767,0.002977199,0.00118472,0.0009690022,0.00006141167,0.001141501,0.000242247],"genre_scores_gemma":[0.2675811,0.04290103,0.6704195,0.000634559,0.003425749,0.001261913,0.0005692504,0.0006112201,0.01259576],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.597564,"threshold_uncertainty_score":0.9997078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03359863346220957,"score_gpt":0.3339601558951198,"score_spread":0.3003615224329102,"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."}}