no code implementations • 13 Jan 2024 • Yuen-Fui Lau, Tianjia Zhang, Zhefan Rao, Qifeng Chen
The latent code extracted from the degraded input image often contains corrupted features, making it difficult to align the semantic information from the input with the high-quality textures from the reference.
no code implementations • 2 Dec 2023 • Qiang Wen, Yazhou Xing, Zhefan Rao, Qifeng Chen
Specifically, to tailor the pre-trained latent diffusion model to operate on the RAW domain, we train a set of lightweight taming modules to inject the RAW information into the diffusion denoising process via modulating the intermediate features of UNet.
no code implementations • 18 Aug 2022 • Quanshi Zhang, Xu Cheng, Yilan Chen, Zhefan Rao
This paper provides a new perspective to explain the success of knowledge distillation, i. e., quantifying knowledge points encoded in intermediate layers of a DNN for classification, based on the information theory.
no code implementations • CVPR 2020 • Xu Cheng, Zhefan Rao, Yilan Chen, Quanshi Zhang
Whereas, in the scenario of learning from raw data, the DNN learns visual concepts sequentially.