Xiangyu Zhang received his PhD degree from Xi'an Jiaotong University in 2017, and currently is the leader of Foundation Model team in MEGVII Research. His research interests mainly focus on deep learning models for practical vision tasks, especially efficient neural architecture design, AutoML/NAS and CNN backbones for detection/segmentation/face tasks, etc. He has proposed a series of widely used CNN architectures and algorithms such as ResNets/ ShuffleNets/ RepVGG. He won the Best Paper Award in CVPR 2016. His total number of Google Scholar citations is over 180,000.
研究方向
Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningAdvanced Image and Video Retrieval TechniquesAdversarial Robustness in Machine LearningMultimodal Machine Learning Applications
