212 citations · 321 across the 12 of their papers we have counts for
12 papers
SGD with Partial Hessian for Deep Neural Networks Optimization
Ying Sun, Hongwei Yong, Lei Zhang
Due to the effectiveness of second-order algorithms in solving classical optimization problems, designing second-order optimizers to train deep neural networks (DNNs) has attracted…
Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
Lingchen Sun, Rongyuan Wu, Jie Liang +3
The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However,…
Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective
Lingchen Sun, Jie Liang, Shuaizheng Liu +2
High perceptual quality and low distortion degree are two important goals in image restoration tasks such as super-resolution (SR). Most of the existing SR methods aim to achieve t…
Spatial-Frequency Attention for Image Denoising
Shi Guo, Hongwei Yong, Xindong Zhang +2
The recently developed transformer networks have achieved impressive performance in image denoising by exploiting the self-attention (SA) in images. However, the existing methods m…
Unfolded Deep Kernel Estimation for Blind Image Super-resolution
Hongyi Zheng, Hongwei Yong, Lei Zhang
Blind image super-resolution (BISR) aims to reconstruct a high-resolution image from its low-resolution counterpart degraded by unknown blur kernel and noise. Many deep neural netw…
Deep Variational Network Toward Blind Image Restoration
Zongsheng Yue, Hongwei Yong, Qian Zhao +3
Blind image restoration (IR) is a common yet challenging problem in computer vision. Classical model-based methods and recent deep learning (DL)-based methods represent two differe…
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
Hongwei Yong, Jianqiang Huang, Xiansheng Hua +1
Optimization techniques are of great importance to effectively and efficiently train a deep neural network (DNN). It has been shown that using the first and second order statistics…
Variational Denoising Network: Toward Blind Noise Modeling and Removal
Zongsheng Yue, Hongwei Yong, Qian Zhao +2
Blind image denoising is an important yet very challenging problem in computer vision due to the complicated acquisition process of real images. In this work we propose a new varia…
Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model
Jianrui Cai, Hui Zeng, Hongwei Yong +2
Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated…
Model Inconsistent but Correlated Noise: Multi-view Subspace Learning with Regularized Mixture of Gaussians
Hongwei Yong, Deyu Meng, Jinxing Li +2
Multi-view subspace learning (MSL) aims to find a low-dimensional subspace of the data obtained from multiple views. Different from single view case, MSL should take both common an…
Sharp Attention Network via Adaptive Sampling for Person Re-identification
Chen Shen, Guo-Jun Qi, Rongxin Jiang +4
In this paper, we present novel sharp attention networks by adaptively sampling feature maps from convolutional neural networks (CNNs) for person re-identification (re-ID) problem.…
Robust Online Matrix Factorization for Dynamic Background Subtraction
Hongwei Yong, Deyu Meng, Wangmeng Zuo +1
We propose an effective online background subtraction method, which can be robustly applied to practical videos that have variations in both foreground and background. Different fr…