3 papers
cs.LG2024
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
Enneng Yang, Li Shen, Zhenyi Wang +5
Model merging-based multitask learning (MTL) offers a promising approach for performing MTL by merging multiple expert models without requiring access to raw training data. However…
cs.CV2023
Towards Real-World Blind Face Restoration with Generative Diffusion Prior
Xiaoxu Chen, Jingfan Tan, Tao Wang +3
Blind face restoration is an important task in computer vision and has gained significant attention due to its wide-range applications. Previous works mainly exploit facial priors…
cs.CV2023
Blind Face Restoration for Under-Display Camera via Dictionary Guided Transformer
Jingfan Tan, Xiaoxu Chen, Tao Wang +3
By hiding the front-facing camera below the display panel, Under-Display Camera (UDC) provides users with a full-screen experience. However, due to the characteristics of the displ…