{"id":"W3216889993","doi":"10.1109/tcds.2021.3131045","title":"Recurrent Network Knowledge Distillation for Image Rain Removal","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive and Developmental Systems","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Xiamen University; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Computer science; Block (permutation group theory); Streak; Residual; Artificial intelligence; Convolutional neural network; Image (mathematics); Artificial neural network; Channel (broadcasting); Computer vision; Deep learning; Pattern recognition (psychology); Machine learning; Algorithm; Mathematics; Telecommunications","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":[],"consensus_categories":[],"category_scores_codex":[0.0002562205,0.0001670662,0.0001799815,0.00006992809,0.0003408471,0.0001916037,0.0001025123,0.0000577445,0.0000098351],"category_scores_gemma":[0.00001407427,0.0001700943,0.00005827064,0.0003079884,0.0000411653,0.0003405978,0.000006503185,0.0000977208,0.00003580816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001161664,"about_ca_system_score_gemma":0.000127627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005308049,"about_ca_topic_score_gemma":0.00002084065,"domain_scores_codex":[0.9988085,0.00009917632,0.0002691013,0.0004226971,0.0001532492,0.0002472604],"domain_scores_gemma":[0.9992598,0.0002505018,0.00006194537,0.0001003977,0.0002552725,0.00007213114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001840841,0.0006317848,0.00004688138,0.000435935,0.0002841505,0.0001248732,0.002527131,0.00004924498,0.01443222,0.003780017,0.0050612,0.9724425],"study_design_scores_gemma":[0.006684468,0.001167672,0.001182323,0.00440498,0.0001859051,0.001731488,0.003022369,0.0885892,0.8305141,0.002131895,0.05751086,0.002874687],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003355787,0.0004313293,0.9909182,0.00005065427,0.001170953,0.0006244814,0.0000352897,0.0001859787,0.003227284],"genre_scores_gemma":[0.9363199,0.0001173528,0.06133678,0.0000746861,0.0001032696,0.0003721528,0.00002418203,0.00001706839,0.001634576],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9695678,"threshold_uncertainty_score":0.6936246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02568946939497541,"score_gpt":0.2803272227409553,"score_spread":0.2546377533459799,"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."}}