{"id":"W4391697048","doi":"10.1109/tip.2024.3362153","title":"UCL-Dehaze: Toward Real-World Image Dehazing via Unsupervised Contrastive Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Shenzhen Science and Technology Innovation Program; National Defense Basic Scientific Research Program of China; Lingnan University; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Image editing; Embedding; Image (mathematics); Generalization; Leverage (statistics); Deep learning; Computer vision; Pattern recognition (psychology); Mathematics","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":[0.0009374526,0.0008897416,0.0005040363,0.000522976,0.0002916594,0.0005720377,0.001576073,0.001022911,0.00122965],"category_scores_gemma":[0.00231874,0.0003585486,0.0005698422,0.0002461085,0.001087871,0.001738966,0.001567873,0.001971985,0.0004558909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005782827,"about_ca_system_score_gemma":0.0004327628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001565309,"about_ca_topic_score_gemma":0.002804541,"domain_scores_codex":[0.9997399,0.00004829891,0.00000806594,0.00008584728,0.00008717166,0.00003066893],"domain_scores_gemma":[0.999202,0.0003065104,0.0001101369,0.0001827008,0.0001590034,0.00003965478],"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":[0.0002105914,0.0002444744,0.002112576,0.0002103375,0.00009964385,0.0001525804,0.000165896,0.6311079,0.0573411,0.010709,0.003791219,0.2938548],"study_design_scores_gemma":[0.000006330944,0.00006653378,0.0002346181,0.000009971966,0.000007688466,0.00005026546,0.00001268453,0.980232,0.01535386,0.002934233,0.001083232,0.00000859875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.062082,0.0005560778,0.9321718,0.0002990166,0.00005942242,0.00007457465,0.00008480253,0.001409424,0.003263048],"genre_scores_gemma":[0.6045274,0.0004982022,0.3862464,0.0005650088,0.00006174236,0.0001251901,0.0004391527,0.0002705451,0.007266261],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001576073,"threshold_uncertainty_score":0.004957736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0164759686231717,"score_gpt":0.2886161093988815,"score_spread":0.2721401407757099,"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."}}