I am a Research Scientist at Google Cloud AI in Sunnyvale, CA. Prior to joining Google, I was a researcher in Media Analytics group of NEC Laboratories America. I completed my Ph.D. at University of Michigan under the supervision by professor Honglak Lee. I have broad interest in machine learning and computer vision. Specifically, my research focuses on supervised and unsupervised deep representation learning with applications to computer vision, audio recognition, and text processing, using graphical models that are invariant to many factors of variation for robust perception from complex and multimodal data.
Curriculum Vitae [pdf]
July 2019 ~
Research Scientist, Google Cloud AI
July 2015 ~ July 2019
Researcher, NEC Laboratories America
September 2008 ~ June 2015
Ph.D. in Electrical Engineering: Systems, University of Michigan, Ann Arbor
Thesis advisor : Professor Honglak Lee
March 2003 ~ February 2008
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea
B.S. in Electrical Engineering and Computer Science and Mathematical Science
kihyuks [at] google [dot] com
kihyuk.sohn [at] gmail [dot] com
 Domain Adaptation for Structured Output via Discriminative Patch Representations.
Yi-Hsuan Tsai, Kihyuk Sohn, Samuel Schulter and Manmohan Chandraker
To appear in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019 (oral presentation). [pdf][arXiv]
 Gotta Adapt ’Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild.
Luan Tran, Kihyuk Sohn, Xiang Yu, Xiaoming Liu and Manmohan Chandraker
 Feature Transfer Learning for Face Recognition with Under-Represented Data.
Xi Yin, Xiang Yu, Kihyuk Sohn, Xiaoming Liu and Manmohan Chandraker
 Unsupervised Domain Adaptation for Distance Metric Learning.
Kihyuk Sohn, Wenling Shang, Xiang Yu and Manmohan Chandraker
In International Conference on Learning Representations (ICLR), 2019. [pdf]
 Attentive Conditional Channel-Recurrent Autoencoding for Attribute-Conditioned Face Synthesis.
Wenling Shang and Kihyuk Sohn
 Learning to Adapt Structured Output Space for Semantic Segmentation.
Yi-Hsuan Tsai*, Wei-Chih Hung*, Samuel Schulter, Kihyuk Sohn, Ming-Hsuan Yang and Manmohan Chandraker
 Channel-Recurrent Autoencoding for Image Modeling.
Wenling Shang, Kihyuk Sohn, Yuandong Tian
 Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos.
Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker
 Towards Large-Pose Face Frontalization.
Xi Yin, Xiang Yu, Kihyuk Sohn, Xiaoming Liu, Manmohan Chandraker
 Feature Reconstruction Disentangling for Pose-invariant Face Recognition.
Xi Peng, Xiang Yu, Kihyuk Sohn, Dimitris N. Metaxas, Manmohan Chandraker
 Exploring Normalization in Deep Residual Networks with Concatenated Rectified Linear Units.
Wenling Shang, Justin Chiu, Kihyuk Sohn
In Association for the Advancement of Artificial Intelligence (AAAI), 2017. [pdf]
 Improved Deep Metric Learning with Multi-class N-pair Loss Objective.
 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
 Discriminative Training of Structured Dictionaries via Block Orthogonal Matching Pursuit.
Wenling Shang, Kihyuk Sohn, Honglak Lee, Anna Gilbert
In SIAM International Conference on Data Mining (SDM), 2016 [pdf]
 Learning Structured Output Representation using Deep Conditional Generative Models.
Kihyuk Sohn, Xinchen Yan and Honglak Lee.
 Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction.
Yuting Zhang, Kihyuk Sohn, Ruben Villegas, Gang Pan and Honglak Lee
OpenCV People’s Vote Winning Paper [link]
 Improved Multimodal Deep Learning with Variation of Information.
Kihyuk Sohn, Wenling Shang and Honglak Lee
 Learning to Disentangle Factors of Variation with Manifold Interaction.
Scott Reed, Kihyuk Sohn, Yuting Zhang and Honglak Lee
 Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling.
Kihyuk Sohn*, Andrew Kae*, Honglak Lee and Erik Learned-Miller.
 Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines.
Kihyuk Sohn, Guanyu Zhou, Chansoo Lee, and Honglak Lee.
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2012.)
 Learning Invariant Representations with Local Transformations.
Kihyuk Sohn and Honglak Lee.
 Online Incremental Feature Learning with Denoising Autoencoders.
Guanyu Zhou, Kihyuk Sohn, and Honglak Lee.
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.)
 An interpretation of the Cover and Leung capacity region for the MAC with feedback through stochastic control.
Achilleas Anastasopoulos and Kihyuk Sohn.
 Efficient Learning of Sparse, Distributed, Convolutional Feature Representations for Object Recognition.
Kihyuk Sohn, Dae Yon Jung, Honglak Lee, and Alfred Hero III.
- Github (last updated: 2019.06.24)
- Learning Structured Output Representation using Deep Conditional Generative Models. In NIPS 2015. [pdf][supp][bib][code]
- Improved Multimodal Deep Learning with Variation of Information. In NIPS 2014. [pdf][pdf (full)][bib][github]
- Learning Invariant Representations with Local Transformations. In ICML 2012. [pdf][bib][github]
- Disentangling Boltzmann machine
- GLOC (last updated: 2013.07.24)
- Point-wise Gated Boltzmann machine (last updated: 2013.06.18)