World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
36
Citations
15927
World Ranking
10963
National Ranking
4557

Overview

Kihyuk Sohn is affiliated with Google in the United States and has contributed extensively to the field of computer science, particularly in areas related to computer vision, artificial intelligence, and machine learning. Their research output spans multiple subfields and topics within computer science, reflecting a focus on advanced techniques in vision and learning systems.

The main fields of study associated with their work include:

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Epidemiology
  • Control and Systems Engineering

Key research topics covered in their publications are:

  • Domain Adaptation and Few-Shot Learning
  • Multimodal Machine Learning Applications
  • Generative Adversarial Networks and Image Synthesis
  • Anomaly Detection Techniques and Applications
  • Computer Graphics and Visualization Techniques
  • Advanced Image and Video Retrieval Techniques
  • Advanced Vision and Imaging

Frequent coauthors collaborating with Kihyuk Sohn include:

  • Chunliang Li
  • Tomas Pfister
  • Irfan Essa
  • Jinsung Yoon
  • José Lezama

They have published primarily in venues such as:

  • arXiv (Cornell University)
  • 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Lecture Notes in Computer Science

Recent papers by Kihyuk Sohn demonstrate contributions to semi-supervised learning, anomaly detection, and classification, including:

  • FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020, arXiv (Cornell University))
  • A Simple Semi-Supervised Learning Framework for Object Detection (2020, arXiv (Cornell University))
  • Learning and Evaluating Representations for Deep One-class Classification (2020, arXiv (Cornell University))

These papers are noted for their engagement with learning frameworks that target data efficiency and robustness in machine learning models across various computer vision challenges.

Best Publications

  • Learning structured output representation using deep conditional generative models

    Kihyuk Sohn;Xinchen Yan;Honglak Lee

  • FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

    Kihyuk Sohn;David Berthelot;Chun-Liang Li;Zizhao Zhang

  • Learning to Adapt Structured Output Space for Semantic Segmentation

    Yi-Hsuan Tsai;Wei-Chih Hung;Samuel Schulter;Kihyuk Sohn

  • Improved deep metric learning with multi-class N-pair loss objective

    Kihyuk Sohn

  • CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

    Chun-Liang Li;Kihyuk Sohn;Jinsung Yoon;Tomas Pfister

  • Attribute2Image: Conditional Image Generation from Visual Attributes

    Xinchen Yan;Jimei Yang;Kihyuk Sohn;Honglak Lee

  • Understanding and improving convolutional neural networks via concatenated rectified linear units

    Wenling Shang;Kihyuk Sohn;Diogo Almeida;Honglak Lee

  • ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring

    David Berthelot;Nicholas Carlini;Ekin D. Cubuk;Alex Kurakin

  • Towards Large-Pose Face Frontalization in the Wild

    Xi Yin;Xiang Yu;Kihyuk Sohn;Xiaoming Liu

  • Domain Adaptation for Structured Output via Discriminative Patch Representations

    Yi-Hsuan Tsai;Kihyuk Sohn;Samuel Schulter;Manmohan Chandraker

  • A Simple Semi-Supervised Learning Framework for Object Detection.

    Kihyuk Sohn;Zizhao Zhang;Chun-Liang Li;Han Zhang

  • Feature Transfer Learning for Face Recognition With Under-Represented Data

    Xi Yin;Xiang Yu;Kihyuk Sohn;Xiaoming Liu

  • CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

    Chen Wei;Kihyuk Sohn;Clayton Mellina;Alan Yuille

  • Learning to Disentangle Factors of Variation with Manifold Interaction

    Scott Reed;Kihyuk Sohn;Yuting Zhang;Honglak Lee

  • Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction

    Yuting Zhang;Kihyuk Sohn;Ruben Villegas;Gang Pan

  • Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling

    Andrew Kae;Kihyuk Sohn;Honglak Lee;Erik Learned-Miller

  • ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

    David Berthelot;Nicholas Carlini;Ekin D. Cubuk;Alex Kurakin

  • Online Incremental Feature Learning with Denoising Autoencoders

    Guanyu Zhou;Kihyuk Sohn;Honglak Lee

  • Improved Multimodal Deep Learning with Variation of Information

    Kihyuk Sohn;Wenling Shang;Honglak Lee

  • Learning Invariant Representations with Local Transformations

    Kihyuk Sohn;Honglak Lee

Frequent Co-Authors

Manmohan Chandraker
Manmohan Chandraker University of California, San Diego
Honglak Lee
Honglak Lee University of Michigan–Ann Arbor
Tomas Pfister
Tomas Pfister Google (United States)
Xiaoming Liu
Xiaoming Liu University of North Carolina at Chapel Hill
Jinwoo Shin
Jinwoo Shin Korea Advanced Institute of Science and Technology
Ming-Hsuan Yang
Ming-Hsuan Yang University of California, Merced
Nicholas Carlini
Nicholas Carlini Google (United States)
Colin Raffel
Colin Raffel University of Toronto
Ekin D. Cubuk
Ekin D. Cubuk Google (United States)
Erik Learned-Miller
Erik Learned-Miller University of Massachusetts Amherst

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

Studying Computer Science in the USA opens the door to a range of related online degrees and promising career pathways. If you're interested in sustainability and science, an environmental science degree can equip you for in-demand roles that tackle global environmental issues through technology and data analysis.

For those looking to fast-track their tech career, consider a computer science accelerated program. These online courses allow you to earn your degree more quickly and enter the workforce sooner, which is ideal in today’s quickly-evolving tech landscape.

Engineering pathways are also a strong option. You can specialize with environmental engineering degrees online to focus on sustainable innovation, or explore core engineering fundamentals with the cheapest mechanical engineering degree online for access to versatile, high-demand engineering roles.

These online degrees expand your skills and career prospects, offering flexibility for working professionals and diverse opportunities across STEM fields.

Best Scientists Citing Kihyuk Sohn

Trending Scientists

Recently Published Articles