Bio

Hi! My name is Grace (a.k.a Gege). I am currently a research staff at National Laboratory of Pattern Recognition (NLPR) in the Institute of Automation (IA), Chinese Academy of Sciences (CAS), Beijing, China, working with Prof. Dr. Ran He. I'll be a Ph.D. student in the Autonomous Vision Group (AVG) starting Spring 2022, advised by Prof. Dr. Andreas Geiger.

My research interest is at the intersection of vision and learning. Currently, my research focuses on controllable image synthesis, as it provides a way to bridge the human will with artificial machines. I'm also working on causal representation learning to achieve better control and generalization ability in generative modeling.

Prior to NLPR, I studied in two Chinese "Excellent" departments of statistics in Beijing, i.e., School of Statistics, Renmin University of China (M.Sc. 2020) and School of Mathematics and Statistics, Central University of Finance and Economics (B.Sc. 2017), where I majored in Applied Statistics.

Autonomous Vision Group (AVG)
Spring 2022
Autonomous Vision Group (AVG)
Ph.D. Student
3D-Aware Visual Representations
Institute of Automation, Chinese Academy of Sciences (CAS)
Summer 2020-Spring 2022
Institute of Automation, Chinese Academy of Sciences (CAS)
Research Staff
Group Leader: Prof. Dr. Ran He; worked on controllable image synthesis
Peking University
Fall 2019-Spring 2020
Peking University
Research Intern
Host: Prof. Dr. Yongtao Wang; worked on learning semantic representations from comic/manga and cross-domain image synthesis
SenseTime
Summer 2019
SenseTime
Research Intern
Worked on statistical inference from structured medical/underwriting data
Intelligence Qubic
Summer 2018
Intelligence Qubic
Research Intern
Responsible for applying evolutionary algorithms on differentiable NAS to improve the performance of AutoML models
China Galaxy Securities
Fall 2017
China Galaxy Securities
Data Analysis Intern
Worked on data mining for statistical modeling in the Internet Finance Department

Publications

Causal Representation Learning for Context-Aware Face Transfer

Causal Representation Learning for Context-Aware Face Transfer

Gege Gao, Huaibo Huang, Chaoyou Fu, Ran He
Preprint

Human face synthesis involves transferring knowledge about the identity and identity-dependent shape of a human face to target face images where the context (\eg, facial expressions, head poses, and other background factors) may change dramatically. Human faces are non-rigid, so facial expression leads to deformation of face shape, and head pose also affects the face observed in 2D images. A key challenge in face transfer is to match the face with unobserved new contexts, adapting the identity-dependent face shape (IDFS) to different poses and expressions accordingly. In this work, we find a way to provide prior knowledge for generative models to reason about the appropriate appearance of a human face in response to various expressions and poses. We propose a novel context-aware face transfer model, called CarTrans, that incorporates causal effects of contextual factors into face representation, and thus is able to be aware of the uncertainty of new contexts. We estimate the effect of facial expression and head pose in terms of counterfactuals by designing a controlled intervention trial, thus avoiding the need for dense multi-view observations to cover the pose-expression space well. Moreover, we propose a kernel regression-based encoder that eliminates the identity specificity of the target face when encoding contextual information from the target image. The resulting method shows impressive performance, allowing fine-grained control over face shape and appearance under various contextual conditions.

Information Bottleneck Disentanglement for Identity Swapping

Information Bottleneck Disentanglement for Identity Swapping

Gege Gao, Huaibo Huang, Chaoyou Fu, Zhaoyang Li, Ran He
CVPR 2021

Improving the performance of face forgery detectors often requires more identity-swapped images of higher-quality. One core objective of identity swapping is to generate identity-discriminative faces that are distinct from the target while identical to the source. To this end, properly disentangling identity and identity-irrelevant information is critical and remains a challenging endeavor. In this work, we propose a novel information disentangling and swapping network, called InfoSwap, to extract the most expressive information for identity representation from a pre-trained face recognition model. The key insight of our method is to formulate the learning of disentangled representations as optimizing an information bottleneck trade-off, in terms of finding an optimal compression of the pre-trained latent features. Moreover, a novel identity contrastive loss is proposed for further disentanglement by requiring a proper distance between the generated identity and the target. While the most prior works have focused on using various loss functions to implicitly guide the learning of representations, we demonstrate that our model can provide explicit supervision for learning disentangled representations, achieving impressive performance in generating more identity-discriminative swapped faces.

* = Equal contribution

Education

M.Sc. in Applied Statistics, 2020

  • School of Statistics
  • Renmin University of China

B.Sc. in Applied Statistics, 2017

  • School of Mathematics and Statistics
  • Central University of Finance and Economics

Misc

I was born in Beijing, China. My Chinese name is Gege Gao (高格格). Hešeri (赫舍里) is my ancestral surname.

The source code for this website is forked from this repo.