{"id":"W4283815594","doi":"10.1609/aaai.v36i3.20276","title":"Efficient Model-Driven Network for Shadow Removal","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Science and Technology of China; National Natural Science Foundation of China","keywords":"Shadow (psychology); Interpretability; Computer science; Artificial intelligence; Convolutional neural network; Task (project management); Computer vision; Deep learning; Point (geometry); Shadow mapping; FLOPS; Image (mathematics); Algorithm; 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":[0.0002471971,0.0008714843,0.000735542,0.0003484332,0.0003029165,0.0004727132,0.001411513,0.0006985791,0.003332069],"category_scores_gemma":[0.0006316816,0.00048467,0.0007278066,0.0003395764,0.0003285191,0.000814289,0.001006389,0.001222929,0.0007901565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044359,"about_ca_system_score_gemma":0.001421238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01165888,"about_ca_topic_score_gemma":0.02142215,"domain_scores_codex":[0.9998283,0.00001649223,0.000005377271,0.00005022305,0.00006525517,0.0000343867],"domain_scores_gemma":[0.9998472,0.00004292233,0.00001643834,0.00002992041,0.00004818731,0.00001530488],"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":[0.0001186693,0.00006697268,0.0004612963,0.00008555405,0.00006543106,0.0001071205,0.00004310412,0.7723256,0.02057168,0.004305142,0.005446163,0.1964032],"study_design_scores_gemma":[0.000002129763,0.000004462768,0.00002576801,9.560108e-7,0.000002726254,0.000008037979,0.000001490588,0.9977804,0.001099097,0.0007460663,0.0003272778,0.000001602385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01739118,0.0003817647,0.9756846,0.0001750856,0.00007405865,0.00004424206,0.0001435359,0.00318543,0.002920078],"genre_scores_gemma":[0.6413545,0.0004234352,0.3426087,0.0004414994,0.0000842485,0.0001511624,0.001072161,0.000630275,0.01323389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01165888,"threshold_uncertainty_score":0.02318203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07048946113948087,"score_gpt":0.2968550373924375,"score_spread":0.2263655762529566,"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."}}