World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
38
Citations
32681
World Ranking
9921
National Ranking
4167

Overview

Xiaohua Zhai is affiliated with Google in the United States and has contributed extensively to the field of computer science, with a strong focus on computer vision and artificial intelligence. Their research spans multiple subfields including computer vision and pattern recognition, artificial intelligence, radiology, nuclear medicine and imaging, materials chemistry, and electrical and electronic engineering.

Their work involves several main research topics such as domain adaptation and few-shot learning, multimodal machine learning applications, advanced neural network applications, advanced image and video retrieval techniques, natural language processing techniques, COVID-19 diagnosis using AI, and topic modeling.

Frequent coauthors collaborating with Xiaohua Zhai include Lucas Beyer, Neil Houlsby, А. И. Колесников, Andreas Steiner, and Ibrahim Alabdulmohsin, indicating a collaborative approach across diverse teams and research focuses.

Publications by Xiaohua Zhai have appeared primarily in the following venues:

  • arXiv (Cornell University)
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Lecture Notes in Computer Science
  • International Journal of Computer Vision
  • ACS Nano

Significant recent papers include:

  • "Scaling Vision Transformers," 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • "LiT: Zero-Shot Transfer with Locked-image text Tuning," 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • "MLP-Mixer: An all-MLP Architecture for Vision," 2021, arXiv (Cornell University)
  • "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale," 2020, arXiv (Cornell University)
  • "Underspecification Presents Challenges for Credibility in Modern Machine Learning," 2020, arXiv (Cornell University)

The volume and scope of their publications demonstrate active engagement with ongoing advancements in vision transformer models and challenges in machine learning credibility. Xiaohua Zhai has contributed to foundational research shaping domain adaptation, multimodal learning, and neural network architectures.

Their academic footprint reflects a balance between theoretical frameworks and transformative applications across machine learning disciplines, focusing on both performance and transferability of models in computer vision and related fields.

Best Publications

  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

    Alexey Dosovitskiy;Lucas Beyer;Alexander Kolesnikov;Dirk Weissenborn

  • MLP-Mixer: An all-MLP Architecture for Vision

    Ilya Tolstikhin;Neil Houlsby;Alexander Kolesnikov;Lucas Beyer

  • Big Transfer (BiT): General Visual Representation Learning

    Alexander Kolesnikov;Lucas Beyer;Xiaohua Zhai;Joan Puigcerver

  • Revisiting Self-Supervised Visual Representation Learning

    Alexander Kolesnikov;Xiaohua Zhai;Lucas Beyer

  • Scaling Vision Transformers

    Xiaohua Zhai;Alexander Kolesnikov;Neil Houlsby;Lucas Beyer

  • S4L: Self-Supervised Semi-Supervised Learning

    Lucas Beyer;Xiaohua Zhai;Avital Oliver;Alexander Kolesnikov

  • PaLI: A Jointly-Scaled Multilingual Language-Image Model

    Unknown

  • Underspecification Presents Challenges for Credibility in Modern Machine Learning

    Alexander D'Amour;Katherine A. Heller;Dan Moldovan;Ben Adlam

  • Sigmoid Loss for Language Image Pre-Training

    Unknown

  • Self-Supervised GANs via Auxiliary Rotation Loss

    Ting Chen;Xiaohua Zhai;Marvin Ritter;Mario Lucic

  • LiT: Zero-Shot Transfer with Locked-image Text Tuning

    Xiaohua Zhai;Xiao Wang;Basil Mustafa;Andreas Steiner

  • Scaling Vision Transformers to 22 Billion Parameters

    Unknown

  • S4L: Self-Supervised Semi-Supervised Learning

    Xiaohua Zhai;Avital Oliver;Alexander Kolesnikov;Lucas Beyer

  • Learning Cross-Media Joint Representation With Sparse and Semisupervised Regularization

    Xiaohua Zhai;Yuxin Peng;Jianguo Xiao

  • Simple Open-Vocabulary Object Detection

    Unknown

  • A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

    Xiaohua Zhai;Joan Puigcerver;Alexander Kolesnikov;Pierre Ruyssen

  • Knowledge distillation: A good teacher is patient and consistent

    Lucas Beyer;Xiaohua Zhai;Amélie Royer;Larisa Markeeva

  • Semi-Supervised Cross-Media Feature Learning With Unified Patch Graph Regularization

    Yuxin Peng;Xiaohua Zhai;Yunzhen Zhao;Xin Huang

  • The GAN Landscape: Losses, Architectures, Regularization, and Normalization

    Karol Kurach;Mario Lucic;Xiaohua Zhai;Marcin Michalski

  • Heterogeneous metric learning with joint graph regularization for cross-media retrieval

    Xiaohua Zhai;Yuxin Peng;Jianguo Xiao

  • High-Fidelity Image Generation With Fewer Labels

    Mario Lucic;Michael Tschannen;Marvin Ritter;Xiaohua Zhai

  • Are we done with ImageNet

    Lucas Beyer;Olivier J. Hénaff;Alexander Kolesnikov;Xiaohua Zhai

  • A Large-Scale Study on Regularization and Normalization in GANs

    Karol Kurach;Mario Lučić;Xiaohua Zhai;Marcin Michalski

  • The Visual Task Adaptation Benchmark

    Xiaohua Zhai;Joan Puigcerver;Alexander Kolesnikov;Pierre Ruyssen

Frequent Co-Authors

Mario Lucic
Mario Lucic Google (United States)
Sylvain Gelly
Sylvain Gelly Google (United States)
Yuxin Peng
Yuxin Peng Peking University
Jianguo Xiao
Jianguo Xiao Peking University
Alexey Dosovitskiy
Alexey Dosovitskiy Google (United States)
Daniel Keysers
Daniel Keysers Google (United States)
Hugo Larochelle
Hugo Larochelle Google (United States)
Dustin Tran
Dustin Tran Google (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring computer science in the USA opens doors to a range of related fields. Students often branch into disciplines like data science, engineering, or physics, discovering new career options through flexible online programs. With the demand for STEM professionals rising, online education has made degree pathways more accessible and affordable than ever.

If you're interested in engineering, consider the cheapest mechanical engineering degree online options to keep costs manageable. Similarly, a bachelor of science in physics online can be a great fit for those who wish to pursue analytical or research-based roles.

Data science is another rapidly growing area. Many universities now offer dedicated data science degrees online, allowing students to specialize in big data, machine learning, and analytics. Those with an interest in electronics might prefer to explore programs featured in the online electrical engineering degree ranking, which highlights top accredited programs.

Regardless of your chosen path, online STEM degrees provide the flexibility and credentials needed to advance in today's tech-driven workforce.

Best Scientists Citing Xiaohua Zhai

Trending Scientists

Recently Published Articles