{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0003482228,0.0005777616,0.0006251537,0.0001555738,0.0004122425,0.0008178758,0.004931579,0.0006326347,0.00005660257],"category_scores_gemma":[0.000183289,0.0004722792,0.0001621376,0.0004675386,0.0002847925,0.0006771322,0.0082945,0.0007796015,0.00004760555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001838379,"about_ca_system_score_gemma":0.0003477196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001668555,"about_ca_topic_score_gemma":0.00001876909,"domain_scores_codex":[0.9967177,0.0001544796,0.0004902525,0.00161503,0.0005100629,0.0005124644],"domain_scores_gemma":[0.9948102,0.0004026323,0.0005276021,0.002860521,0.001190604,0.0002084351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002092125,0.0004198544,0.00005826604,0.0006687381,0.0001577136,0.00003082535,0.00197825,0.00309784,0.001765501,0.2301472,0.4680421,0.2934245],"study_design_scores_gemma":[0.00019762,0.0002351256,0.00003563956,0.0007343582,0.00001852526,0.000008387591,0.0001051625,0.4453522,0.1836101,0.2202679,0.1483546,0.001080354],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008588901,0.0006539385,0.9898632,0.001027418,0.001386357,0.001878227,0.0001925815,0.001433093,0.003479257],"genre_scores_gemma":[0.009467405,0.0001363948,0.9879606,0.0005279739,0.0002443692,0.0006408245,0.0001905194,0.00004438178,0.0007875829],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4422543,"threshold_uncertainty_score":0.9997729,"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."}}