Lixin Duan

Also published under:Ling-Yu Duan, Lingyu Duan, L. -Y. Duan, Ling-yu Duan

Affiliation

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China

Topic

Domain Adaptation,Semantic Segmentation,Source Domain,Target Domain,Convolutional Neural Network,Domain Gap,Feature Maps,Pseudo Labels,Deep Neural Network,Training Set,Adversarial Training,Benchmark Datasets,Bounding Box,Clear Image,Color Distortion,Computer Vision,Cross-entropy Loss,Data Sources,Deep Learning,Feature Fusion,High-level Features,Learning Rate,Low-level Features,Multi-scale Features,Neural Network,Object Detection,Original Features,Segmentation Performance,Semantic Information,Target Sample,Training Data,Absorption Effects,Atrous Spatial Pyramid Pooling,Attack Success,Attention Mechanism,Backbone Feature,Backbone Network,Background Scene,Class Separation,Color Jittering,Compact Representation,Computational Cost,Convolutional Neural Networks Backbone,Decoding,Deep Network,Depth Features,Depth Information,Dilated Convolution,Discrete Cosine Transform,Domain Discrepancy,

Biography

Ling-Yu Duan is currently a Full Professor with the National Engineering Laboratory of Video Technology, School of Electronics Engineering and Computer Science, Peking University (PKU), Beijing, China. He was the Associate Director with the Rapid-Rich Object Search Laboratory, a joint lab between Nanyang Technological University, Singapore, and PKU since 2012. Contact him at [email protected].