{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005194457,0.0007941384,0.00067884,0.000452973,0.0002542626,0.0004005753,0.001270067,0.0007340568,0.001605009],"category_scores_gemma":[0.001416821,0.0003281535,0.0005838494,0.0003953863,0.0003595751,0.0009760365,0.0007534419,0.001145624,0.0004016751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005770557,"about_ca_system_score_gemma":0.0008042484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009159703,"about_ca_topic_score_gemma":0.01402023,"domain_scores_codex":[0.9997951,0.00003058647,0.00001116115,0.00006779721,0.00005618732,0.00003916235],"domain_scores_gemma":[0.9996222,0.0001488129,0.00004688978,0.00006390379,0.00009647841,0.00002173035],"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":[0.0002302869,0.000173209,0.0009425568,0.0001227481,0.0001270584,0.0001972353,0.0001101398,0.3897144,0.03233893,0.004242934,0.003615833,0.5681847],"study_design_scores_gemma":[0.000005234982,0.00003676064,0.0001796829,0.00000386996,0.00002154227,0.00002385322,0.000005922741,0.9906802,0.007331309,0.001148409,0.0005576911,0.000005563221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05696161,0.0008678591,0.9371777,0.0002469904,0.00006485661,0.00004887181,0.000129049,0.002667954,0.001835167],"genre_scores_gemma":[0.7711621,0.0005522013,0.2208478,0.0003272313,0.00006578012,0.00009129303,0.0007097772,0.000160089,0.006083621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009159703,"threshold_uncertainty_score":0.0182128,"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."}}