Yanqi Ge

I am currently an algorithm engineer at Tencent, where I am responsible for researching and developing algorithms in computer vision. I received MS degree from University of Electronic Science and Technology of China in 2024, under the supervision of Prof. Lixin Duan.

I sincerely welcome scientific collaborations. If you're interested, please feel free to reach out to me via email or WeChat (yanq16).

Email / Github / Google Scholar

Working Experience

Tencent, Tencent Map, Engineer, 2024.07-Now

VIVO, 3D Photography Research Center, Research Intern, 2023.08-2023.12

Tencent, Youtu Lab, Research Intern, 2023.03-2023.08

Publications

My research interests include semantic segmentation and AIGC.

Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
Yanqi Ge*, Jiaqi Liu*, Qingnan Fan, Xi Jiang, Ye Huang, Shuai Qin, Hong Gu, Wen Li, Lixin Duan
Under Review, 2025
paper

We introduce a text-driven tuning-free style transfer framework.

Notice: The revision has not been uploaded yet.

SSR: SAM is a Strong Regularizer for domain adaptive semantic segmentation
Yanqi Ge*, Ye Huang*, Wen Li, Lixin Duan
IEEE CAI, 2024
paper code

We introduced SSR, which utilizes SAM as a strong regularizer during training, to greatly enhance the robustness of the image encoder for handling various domains.

Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning
Yanqi Ge*, Qiang Nie*, Ye Huang, Yong Liu, Chengjie Wang, Feng Zheng, Wen Li, Lixin Duan.
AAAI, 2024
paper code

We proposed a Semantic Anchor Regularization (SAR) to improve the representation learning of semantic segmentation.

Thanks the original template from jonbarron.