{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008217829,0.0004831989,0.000492457,0.000811236,0.0008520939,0.000315294,0.0009844308,0.00009510125,0.0003314367],"category_scores_gemma":[0.000002938542,0.0005540205,0.0003392724,0.001505454,0.00006727687,0.001372262,0.000003202894,0.0006341006,0.0001219585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006656661,"about_ca_system_score_gemma":0.0001761566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003689452,"about_ca_topic_score_gemma":0.0009752265,"domain_scores_codex":[0.995499,0.0002996438,0.001315996,0.0008999881,0.001294164,0.0006912549],"domain_scores_gemma":[0.9981787,0.0001106521,0.0004127963,0.0008579304,0.0002270881,0.0002128521],"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":[0.0003322399,0.001830337,0.0001953466,0.0004438749,0.0003499435,0.0002160007,0.01184356,0.7885858,0.04462213,0.003891418,0.0007138586,0.1469755],"study_design_scores_gemma":[0.0008049621,0.0005283645,0.0005231122,0.000121001,0.000117241,0.00003872971,0.0004908026,0.5847526,0.4092364,0.0009686997,0.001471834,0.0009463149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01482829,0.00004397479,0.9783617,0.0003031235,0.002408826,0.001326576,0.0001235319,0.001647869,0.000956135],"genre_scores_gemma":[0.9715513,0.00006742331,0.02645354,0.0001618175,0.00006927522,0.001085793,0.00009374009,0.00007408715,0.0004430311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.956723,"threshold_uncertainty_score":0.9996911,"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."}}