{"id":"W4285261750","doi":"10.1109/tits.2022.3170328","title":"Cycle-SNSPGAN: Towards Real-World Image Dehazing via Cycle Spectral Normalized Soft Likelihood Estimation Patch GAN","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Leverage (statistics); Computer vision; Image (mathematics); Image editing","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":[0.0005053824,0.0007166212,0.0005061192,0.0002729344,0.0001416274,0.0003994268,0.001162353,0.0006036438,0.002049353],"category_scores_gemma":[0.001020175,0.0002837007,0.0005244381,0.0001845115,0.0006942628,0.0007585663,0.001151203,0.001390429,0.0005523607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004779135,"about_ca_system_score_gemma":0.000354285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001939908,"about_ca_topic_score_gemma":0.003077582,"domain_scores_codex":[0.9998159,0.00004498089,0.000004776901,0.00005174179,0.00006141186,0.0000213242],"domain_scores_gemma":[0.9996828,0.0001293002,0.00003146028,0.00007484092,0.00005411295,0.00002747188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001226193,0.00006977091,0.0008566665,0.0000900677,0.00006772362,0.0001167053,0.00007337489,0.8690588,0.01832267,0.01015696,0.005203084,0.09586152],"study_design_scores_gemma":[0.000002832934,0.000016325,0.00007717958,0.000003079623,0.000003206852,0.00002576922,0.00000360447,0.9954243,0.001926514,0.00204342,0.0004705173,0.00000320072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02949311,0.0002568067,0.9649338,0.0001784697,0.00004630552,0.00004808661,0.0001221282,0.001276048,0.003645294],"genre_scores_gemma":[0.7120682,0.0003439616,0.2747279,0.0005533634,0.00004558931,0.0001169682,0.0008143753,0.0005012653,0.01082848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002049353,"threshold_uncertainty_score":0.006855786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01382570413562358,"score_gpt":0.2671288536452248,"score_spread":0.2533031495096013,"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."}}