{"id":"W3022325505","doi":"10.1109/tpami.2021.3125692","title":"A Little Bit More: Bitplane-Wise Bit-Depth Recovery","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Residual; Computer science; Artificial intelligence; Quantization (signal processing); Encoding (memory); Color depth; Image (mathematics); Bit (key); Deep learning; Bitstream; Computer vision; Algorithm; Decoding methods; Image processing; Color image","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"],"consensus_categories":[],"category_scores_codex":[0.0002920098,0.0005769453,0.000831444,0.001165705,0.0002661522,0.0007094347,0.001042439,0.0002118533,0.0003140321],"category_scores_gemma":[0.00001336396,0.0005316283,0.0007656122,0.001557944,0.0001042579,0.0004235574,0.00008068127,0.001183409,0.00005180317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008846042,"about_ca_system_score_gemma":0.0001053991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00172404,"about_ca_topic_score_gemma":0.001326066,"domain_scores_codex":[0.9965753,0.0001654053,0.0007421744,0.001533685,0.000539043,0.000444382],"domain_scores_gemma":[0.9974592,0.0002118807,0.0002945793,0.00157244,0.000173648,0.0002882657],"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":[0.0000102312,0.0002090269,0.0002161826,0.00006471349,0.0007055563,0.00007599394,0.0004663135,0.07044596,0.0002017646,0.000008655379,0.00002693469,0.9275687],"study_design_scores_gemma":[0.0001749776,0.0001384443,0.0009558111,0.0003603772,0.001028079,0.00006111944,0.0001918223,0.9103432,0.08432195,0.0006867991,0.0005306158,0.001206746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001830211,0.0009430096,0.9945647,0.001079726,0.0009062514,0.0001990822,0.0001211425,0.0002169517,0.0001389046],"genre_scores_gemma":[0.9743005,0.004467473,0.01875139,0.001641171,0.00005357884,0.00005127763,0.00005527578,0.00003691795,0.0006424366],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9758133,"threshold_uncertainty_score":0.9997135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02464318072717642,"score_gpt":0.2953643651417752,"score_spread":0.2707211844145987,"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."}}