71 citations · 172 across the 13 of their papers we have counts for
13 papers
A Deep Variational Bayesian Framework for Blind Image Deblurring
Hui Wang, Zongsheng Yue, Qian Zhao +1
Blind image deblurring is an important yet very challenging problem in low-level vision. Traditional optimization based methods generally formulate this task as a maximum-a-posteri…
Semi-Supervised Video Deraining with Dynamical Rain Generator
Zongsheng Yue, Jianwen Xie, Qian Zhao +1
While deep learning (DL)-based video deraining methods have achieved significant success recently, they still exist two major drawbacks. Firstly, most of them do not sufficiently m…
Meta Feature Modulator for Long-tailed Recognition
Renzhen Wang, Kaiqin Hu, Yanwen Zhu +3
Deep neural networks often degrade significantly when training data suffer from class imbalance problems. Existing approaches, e.g., re-sampling and re-weighting, commonly address…
Learning to Purify Noisy Labels via Meta Soft Label Corrector
Yichen Wu, Jun Shu, Qi Xie +2
Recent deep neural networks (DNNs) can easily overfit to biased training data with noisy labels. Label correction strategy is commonly used to alleviate this issue by designing a m…
From Rain Generation to Rain Removal
Hong Wang, Zongsheng Yue, Qi Xie +3
For the single image rain removal (SIRR) task, the performance of deep learning (DL)-based methods is mainly affected by the designed deraining models and training datasets. Most o…
Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
Zongsheng Yue, Qian Zhao, Lei Zhang +1
Real-world image noise removal is a long-standing yet very challenging task in computer vision. The success of deep neural network in denoising stimulates the research of noise gen…
MLR-SNet: Transferable LR Schedules for Heterogeneous Tasks
Jun Shu, Yanwen Zhu, Qian Zhao +2
The learning rate (LR) is one of the most important hyper-parameters in stochastic gradient descent (SGD) algorithm for training deep neural networks (DNN). However, current hand-d…
Meta Transition Adaptation for Robust Deep Learning with Noisy Labels
Jun Shu, Qian Zhao, Zongben Xu +1
To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted la…
Structural Residual Learning for Single Image Rain Removal
Hong Wang, Yichen Wu, Qi Xie +3
To alleviate the adverse effect of rain streaks in image processing tasks, CNN-based single image rain removal methods have been recently proposed. However, the performance of thes…
A Model-driven Deep Neural Network for Single Image Rain Removal
Hong Wang, Qi Xie, Qian Zhao +1
Deep learning (DL) methods have achieved state-of-the-art performance in the task of single image rain removal. Most of current DL architectures, however, are still lack of suffici…
Learning Adaptive Loss for Robust Learning with Noisy Labels
Jun Shu, Qian Zhao, Keyu Chen +2
Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current robust loss functions, however, inevitably involve hyperparameter(s) t…
A Survey on Rain Removal from Video and Single Image
Hong Wang, Yichen Wu, Minghan Li +2
Rain streaks might severely degenerate the performance of video/image processing tasks. The investigations on rain removal from video or a single image has thus been attracting muc…
Discovering Influential Factors in Variational Autoencoders
Shiqi Liu, Jingxin Liu, Qian Zhao +5
In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract…