{"id":"W2798399419","doi":"10.1109/mmsp.2018.8547134","title":"Near-Lossless Deep Feature Compression for Collaborative Intelligence","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Cloud computing; Deep learning; Artificial intelligence; Lossless compression; Inference; Mobile device; Deep neural networks; Software deployment; Codec; Feature (linguistics); Image compression; Artificial neural network; Mobile cloud computing; Computer engineering; Distributed computing; Data compression; Real-time computing; Image (mathematics); Image processing; Computer hardware","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":[0.0003615613,0.0004459348,0.0003050766,0.0003328327,0.000221386,0.000670322,0.0009160073,0.0006366107,0.002483628],"category_scores_gemma":[0.001588292,0.0001546799,0.000231333,0.0005161121,0.0005862053,0.001870563,0.0008990848,0.001182662,0.0005501332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004585314,"about_ca_system_score_gemma":0.0003981273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001620126,"about_ca_topic_score_gemma":0.002971965,"domain_scores_codex":[0.999761,0.00002970101,0.00001149049,0.00003234198,0.0001362009,0.00002924916],"domain_scores_gemma":[0.99953,0.0001655471,0.00004103521,0.0001626428,0.00008081341,0.00002012553],"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":[0.0002932345,0.0002013955,0.001157301,0.0001929613,0.0000647983,0.0003972825,0.0001967437,0.1742406,0.1100917,0.05854961,0.01043777,0.6441766],"study_design_scores_gemma":[0.00001433802,0.0000709125,0.0003610618,0.00001860365,0.000009528274,0.0001755632,0.00002942987,0.9306689,0.04775336,0.01522032,0.005665323,0.00001282311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03496663,0.0004536386,0.9594958,0.0004056037,0.00006614716,0.00003952349,0.0001456871,0.001141847,0.003285076],"genre_scores_gemma":[0.6795667,0.0005471394,0.3121127,0.0003586473,0.00009379468,0.00007790139,0.0003885135,0.0001375691,0.006716987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002483628,"threshold_uncertainty_score":0.008308589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03495862601100915,"score_gpt":0.3393469280271962,"score_spread":0.3043883020161871,"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."}}