no code implementations • 20 May 2024 • Zhigang Jia, Yuelian Xiang, Meixiang Zhao, Tingting Wu, Michael K. Ng
To solve this challenging problem, we present a novel cross-space total variation (CSTV) regularization model for color image deblurring by introducing a quaternion blur operator and a cross-color space regularization functional.
no code implementations • 30 Oct 2023 • Tingting Wu, Zhiyan Du, Zhi Li, Feng-Lei Fan, Tieyong Zeng
However, we empirically find that VDIP struggles with processing image details and tends to generate suboptimal results when the blur kernel is large.
1 code implementation • 18 May 2023 • Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu
To mitigate the effects of label noise, learning with noisy labels (LNL) methods are designed to achieve better generalization performance.
no code implementations • 28 Dec 2022 • Hao Zhang, Tingting Wu, Siyao Cheng, Jie Liu
Federated learning (FL) is an emerging paradigm to train model with distributed data from numerous Internet of Things (IoT) devices.
no code implementations • 11 Oct 2022 • Tingting Wu, Wenna Wu, Ying Yang, Feng-Lei Fan, Tieyong Zeng
In this paper, using a sequential Retinex decomposition strategy, we design a plug-and-play framework based on the Retinex theory for simultaneously image enhancement and noise removal.
no code implementations • 21 Aug 2022 • Tingting Wu, Xiao Ding, Hao Zhang, Jinglong Gao, Li Du, Bing Qin, Ting Liu
To relieve this issue, curriculum learning is proposed to improve model performance and generalization by ordering training samples in a meaningful (e. g., easy to hard) sequence.
1 code implementation • 7 Apr 2022 • Hao Zhang, Tingting Wu, Siyao Cheng, Jie Liu
On the other hand, it enlarges the distances between local models, resulting in an aggregated global model with poor performance.
no code implementations • 17 Mar 2021 • Tingting Wu, Xiaoyu Gu, Jinbo Shao, Ruoxuan Zhou, Zhi Li
The proposed variational method uses a combination of $l_1$ and $l_2$ regularizers to maintain edge information of objects in images while overcoming the staircase effect.