Xiaohua Zhai is currently a staff researcher in Google Research, Brain Team, Zurich. His research interests include representation learning and deep learning. He received the Ph.D degree from Peking University in 2014. As an equal contributor, he proposed "Vision Transformer (ViT)" which applies transformer architectures to image recognition, and it achieves comparable performance to the convolutional neural networks (CNNs). He led the large scale representation learning effort "Big Transfer (BiT)" and "Scaling ViT", which are pre-trained on up to three billion images and achieve good performance across 20 vision tasks. He has authored papers in refereed conference proceedings and international journals, including ICLR, ICML, NeurIPS, ICCV, CVPR and ECCV. He is a reviewer of IEEE TPAMI, TIP, TMM, ICLR, ICML, ICCV, CVPR, ECCV and NeurIPS.
没有数据了, 换个别的吧!
参考链接
微信扫码咨询专知VIP会员