77 citations · 168 across the 24 of their papers we have counts for
24 papers
Locally Regularized Sparse Graph by Fast Proximal Gradient Descent
Dongfang Sun, Yingzhen Yang
Sparse graphs built by sparse representation has been demonstrated to be effective in clustering high-dimensional data. Albeit the compelling empirical performance, the vanilla spa…
Projective Proximal Gradient Descent for A Class of Nonconvex Nonsmooth Optimization Problems: Fast Convergence Without Kurdyka-Lojasiewicz (KL) Property
Yingzhen Yang, Ping Li
Nonconvex and nonsmooth optimization problems are important and challenging for statistics and machine learning. In this paper, we propose Projected Proximal Gradient Descent (PPGD…
Noisy -Sparse Subspace Clustering on Dimensionality Reduced Data
Yingzhen Yang, Ping Li
Sparse subspace clustering methods with sparsity induced by -norm, such as -Sparse Subspace Clustering (-SSC)~\citep{YangFJYH16-L0SSC-ijcv}, are demon…
Bayesian Robust Graph Contrastive Learning
Yancheng Wang, Yingzhen Yang
Graph Neural Networks (GNNs) have been widely used to learn node representations and with outstanding performance on various tasks such as node classification. However, noise, whic…
Benchmark of DNN Model Search at Deployment Time
Lixi Zhou, Arindam Jain, Zijie Wang +3
Deep learning has become the most popular direction in machine learning and artificial intelligence. However, the preparation of training data, as well as model training, are often…
Adaptive Cross-Layer Attention for Image Restoration
Yancheng Wang, Ning Xu, Yingzhen Yang
Non-local attention module has been proven to be crucial for image restoration. Conventional non-local attention processes features of each layer separately, so it risks missing co…
Discriminative Similarity for Data Clustering
Yingzhen Yang, Ping Li
Similarity-based clustering methods separate data into clusters according to the pairwise similarity between the data, and the pairwise similarity is crucial for their performance.…
Adjoined Networks: A Training Paradigm with Applications to Network Compression
Utkarsh Nath, Shrinu Kushagra, Yingzhen Yang
Compressing deep neural networks while maintaining accuracy is important when we want to deploy large, powerful models in production and/or edge devices. One common technique used…
FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary
Yingzhen Yang, Jiahui Yu, Nebojsa Jojic +2
We present a novel method of compression of deep Convolutional Neural Networks (CNNs) by weight sharing through a new representation of convolutional filters. The proposed method r…
An Empirical Study on Regularization of Deep Neural Networks by Local Rademacher Complexity
Yingzhen Yang, Jiahui Yu, Xingjian Li +2
Regularization of Deep Neural Networks (DNNs) for the sake of improving their generalization capability is important and challenging. The development in this line benefits theoreti…
Learning D-FilterMap for Deep Convolutional Neural Networks
Yingzhen Yang, Jianchao Yang, Ning Xu +1
We present a novel and compact architecture for deep Convolutional Neural Networks (CNNs) in this paper, termed D-FilterMap Convolutional Neural Networks (D-FM-CNNs). The con…
WSNet: Compact and Efficient Networks Through Weight Sampling
Xiaojie Jin, Yingzhen Yang, Ning Xu +4
We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model param…
Discriminative Similarity for Clustering and Semi-Supervised Learning
Yingzhen Yang, Feng Liang, Nebojsa Jojic +3
Similarity-based clustering and semi-supervised learning methods separate the data into clusters or classes according to the pairwise similarity between the data, and the pairwise…
On the Suboptimality of Proximal Gradient Descent for Sparse Approximation
Yingzhen Yang, Jiashi Feng, Nebojsa Jojic +2
We study the proximal gradient descent (PGD) method for sparse approximation problem as well as its accelerated optimization with randomized algorithms in this paper. We…
Deep Double Sparsity Encoder: Learning to Sparsify Not Only Features But Also Parameters
Zhangyang Wang, Thomas S. Huang
This paper emphasizes the significance to jointly exploit the problem structure and the parameter structure, in the context of deep modeling. As a specific and interesting example,…
Learning A Deep Encoder for Hashing
Zhangyang Wang, Yingzhen Yang, Shiyu Chang +2
We investigate the -constrained representation which demonstrates robustness to quantization errors, utilizing the tool of deep learning. Based on the Alternating Dire…
Studying Very Low Resolution Recognition Using Deep Networks
Zhangyang Wang, Shiyu Chang, Yingzhen Yang +2
Visual recognition research often assumes a sufficient resolution of the region of interest (ROI). That is usually violated in practice, inspiring us to explore the Very Low Resolu…
: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images
Zhangyang Wang, Ding Liu, Shiyu Chang +3
In this paper, we design a Deep Dual-Domain () based fast restoration model to remove artifacts of JPEG compressed images. It leverages the large learning capacity of…
Learning with -Graph: -Induced Sparse Subspace Clustering
Yingzhen Yang, Jiashi Feng, Jianchao Yang +1
Sparse subspace clustering methods, such as Sparse Subspace Clustering (SSC) \cite{ElhamifarV13} and -graph \cite{YanW09,ChengYYFH10}, are effective in partitioning the d…
Self-Tuned Deep Super Resolution
Zhangyang Wang, Yingzhen Yang, Zhaowen Wang +4
Deep learning has been successfully applied to image super resolution (SR). In this paper, we propose a deep joint super resolution (DJSR) model to exploit both external and self s…
Designing A Composite Dictionary Adaptively From Joint Examples
Zhangyang Wang, Yingzhen Yang, Jianchao Yang +1
We study the complementary behaviors of external and internal examples in image restoration, and are motivated to formulate a composite dictionary design framework. The composite d…
Learning Super-Resolution Jointly from External and Internal Examples
Zhangyang Wang, Yingzhen Yang, Zhaowen Wang +3
Single image super-resolution (SR) aims to estimate a high-resolution (HR) image from a lowresolution (LR) input. Image priors are commonly learned to regularize the otherwise seri…
Epitome for Automatic Image Colorization
Yingzhen Yang, Xinqi Chu, Tian-Tsong Ng +3
Image colorization adds color to grayscale images. It not only increases the visual appeal of grayscale images, but also enriches the information contained in scientific images tha…
Nonparametric Unsupervised Classification
Yingzhen Yang, Thomas S. Huang
Unsupervised classification methods learn a discriminative classifier from unlabeled data, which has been proven to be an effective way of simultaneously clustering the data and tr…