← Search

Ge Yuan

2 accepted papers

2023

Inserting Anybody in Diffusion Models via Celeb Basis

NeurIPS 2023poster

Exquisite demand exists for customizing the pretrained large text-to-image model, $e.g.$ Stable Diffusion, to generate innovative concepts, such as the users themselves. However, the newly-added concept from previous customization methods often shows weaker combination abilities than the original on…

2022

MSML: Enhancing Occlusion-Robustness by Multi-Scale Segmentation-Based Mask Learning for Face Recognition

AAAI 2022technical

In unconstrained scenarios, face recognition remains challenging, particularly when faces are occluded. Existing methods generalize poorly due to the distribution distortion induced by unpredictable occlusions. To tackle this problem, we propose a hierarchical segmentation-based mask learning strate…