I am a Ph.D. student in the Electrical and Computer Engineering Department at the University of California, Los Angeles. I am a member of the Visual Machines Group, advised by Prof. Achuta Kadambi. Before joining UCLA, I received my undergraduate degree at The Hong Kong Polytechnic University, advised by Prof. Wan-Chi Siu.

Research Interest

Despite the remarkable performance of deep learning, the models usually suffer from generalization issues when their training sets are not sufficiently large or diverse. Human intelligence, on the other hand, is capable of learning with a few samples, and one of the potential reasons for this is that we use other prior knowledge to generalize to unseen data and new environments. I am interested in enabling machines with such capability. More specifically, I am working on bridging deep learning with some physical priors and inductive biases for various applications in computer vision, computational imaging, and healthcare.

Papers

(* Indicates equal contribution)

Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation
arXiv, 2021
Yunhao Ba*, Zhen Wang*, Kerim Doruk Karinca, Oyku Deniz Bozkurt, Achuta Kadambi
Deep Shape from Polarization
ECCV, 2020
Yunhao Ba, Alex Gilbert*, Franklin Wang*, Jinfa Yang, Rui Chen, Yiqin Wang, Lei Yan, Boxin Shi, Achuta Kadambi
Visual Physics: Discovering Physical Laws from Videos
arXiv, 2019
Pradyumna Chari*, Chinmay Talegaonkar*, Yunhao Ba*, Achuta Kadambi
Blending Diverse Physical Priors with Neural Networks
arXiv, 2019
Yunhao Ba*, Guangyuan Zhao*, Achuta Kadambi