{"id":"W2919080262","doi":"10.1109/tpami.2019.2903062","title":"Learning Raw Image Reconstruction-Aware Deep Image Compressors","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Artificial intelligence; Computer science; JPEG; Computer vision; RGB color model; Image compression; Iterative reconstruction; Deep learning; Data compression; Image processing; Image (mathematics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004367614,0.0002736877,0.0004328032,0.0005949784,0.0003131136,0.0003840377,0.0005256553,0.0000805693,0.0006673285],"category_scores_gemma":[0.0000079364,0.0002481024,0.0003389059,0.001085837,0.0001000474,0.0006461643,0.00001157422,0.0005383795,0.0002282002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003347076,"about_ca_system_score_gemma":0.00001839178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005946845,"about_ca_topic_score_gemma":0.0001505959,"domain_scores_codex":[0.9979518,0.0003036126,0.0004249706,0.0006945139,0.0003075115,0.0003175657],"domain_scores_gemma":[0.9987004,0.0002776639,0.0001475523,0.0005889771,0.000145651,0.0001397499],"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":[0.0000185607,0.00007416015,0.0006707738,0.00002547779,0.0003523421,0.00002340355,0.000451161,0.02970537,0.007471275,0.00002150792,0.000003202533,0.9611828],"study_design_scores_gemma":[0.000203695,0.0001516551,0.00065311,0.0000329703,0.000255659,0.00006652363,0.000133398,0.7857316,0.2121154,0.0002476096,0.00005016743,0.0003582463],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0137536,0.00005908308,0.9849118,0.000205495,0.0003893097,0.0001325074,0.000007146204,0.0001447736,0.0003962662],"genre_scores_gemma":[0.9743896,0.0001863363,0.02430588,0.0002768012,0.00002109777,0.000010375,0.000003955431,0.0000165964,0.0007894062],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9608245,"threshold_uncertainty_score":0.9999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01377748640631952,"score_gpt":0.2717217225267818,"score_spread":0.2579442361204623,"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."}}