{"id":"W3205467587","doi":"10.1109/tip.2021.3120678","title":"High Frequency Detail Accentuation in CNN Image Restoration","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Image restoration; Computer science; Image (mathematics); Feature (linguistics); Ground truth; Pattern recognition (psychology); Computer vision; Outlier; Feature extraction; Image processing","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":[0.0003087215,0.000272183,0.0002475191,0.0003882214,0.0003946704,0.0008049029,0.0005487844,0.0001201909,0.00003872129],"category_scores_gemma":[0.00007111833,0.0003067648,0.00007248967,0.001624724,0.0001028489,0.006228276,0.000008991035,0.0005146629,0.00005233561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003205496,"about_ca_system_score_gemma":0.0004653911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003176924,"about_ca_topic_score_gemma":0.00006513616,"domain_scores_codex":[0.997742,0.0001303104,0.000519092,0.0007614245,0.0004372202,0.0004099545],"domain_scores_gemma":[0.9984862,0.00006854581,0.0002065357,0.0005912067,0.000559469,0.00008802198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001582862,0.0003550557,0.00001876767,0.0001349523,0.000006858907,0.0001329883,0.0007353714,0.0004446247,0.6079556,0.000312342,0.00004392588,0.3898437],"study_design_scores_gemma":[0.0006418054,0.00005535632,0.0002320745,0.0003546145,0.00001794462,0.00006228197,0.00009429763,0.08577027,0.8888215,0.02339559,0.00004831161,0.0005058816],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002761133,0.0002653408,0.9938492,0.001273182,0.0002966059,0.0001898705,0.000003889474,0.00079688,0.000563922],"genre_scores_gemma":[0.4328918,0.00004342953,0.5666431,0.0001929964,0.00002532971,0.00006881441,0.00000380624,0.00002323806,0.0001075468],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4301307,"threshold_uncertainty_score":0.9999384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01775350805743872,"score_gpt":0.2849806806719641,"score_spread":0.2672271726145254,"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."}}