Nonconvex Sparse Spectral Clustering by Alternating Direction Method of Multipliers and Its Convergence Analysis

Dec 08, 2017

Canyi Lu, Jiashi Feng, Zhouchen Lin, Shuicheng Yan

Dec 08, 2017

Canyi Lu, Jiashi Feng, Zhouchen Lin, Shuicheng Yan

* Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2018

**Click to Read Paper**

Convex Sparse Spectral Clustering: Single-view to Multi-view

May 27, 2018

Canyi Lu, Shuicheng Yan, Zhouchen Lin

May 27, 2018

Canyi Lu, Shuicheng Yan, Zhouchen Lin

* IEEE Transactions on Image Processing (TIP), vol. 25, pp. 2833-2843, 2016

**Click to Read Paper**

In this paper we propose a new method to get the specified network parameters through one time feed-forward propagation of the meta networks and explore the application to neural style transfer. Recent works on style transfer typically need to train image transformation networks for every new style, and the style is encoded in the network parameters by enormous iterations of stochastic gradient descent. To tackle these issues, we build a meta network which takes in the style image and produces a corresponding image transformations network directly. Compared with optimization-based methods for every style, our meta networks can handle an arbitrary new style within $19ms$ seconds on one modern GPU card. The fast image transformation network generated by our meta network is only 449KB, which is capable of real-time executing on a mobile device. We also investigate the manifold of the style transfer networks by operating the hidden features from meta networks. Experiments have well validated the effectiveness of our method. Code and trained models has been released https://github.com/FalongShen/styletransfer.

**Click to Read Paper**
A Focused Dynamic Attention Model for Visual Question Answering

Apr 06, 2016

Ilija Ilievski, Shuicheng Yan, Jiashi Feng

Apr 06, 2016

Ilija Ilievski, Shuicheng Yan, Jiashi Feng

* Submitted to ECCV 2016

**Click to Read Paper**

**Click to Read Paper**

Smoothed Low Rank and Sparse Matrix Recovery by Iteratively Reweighted Least Squares Minimization

Dec 06, 2014

Canyi Lu, Zhouchen Lin, Shuicheng Yan

Dec 06, 2014

Canyi Lu, Zhouchen Lin, Shuicheng Yan

* IEEE Transactions on Image Processing 2015

**Click to Read Paper**

Exact Subspace Segmentation and Outlier Detection by Low-Rank Representation

Mar 30, 2014

Guangcan Liu, Huan Xu, Shuicheng Yan

Mar 30, 2014

Guangcan Liu, Huan Xu, Shuicheng Yan

* Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2012

**Click to Read Paper**

* 10 pages, 4 figures, for iclr2014

**Click to Read Paper**

* To appear in IEEE transactions on Circuits and Systems for Video Technology (T-CSVT)

**Click to Read Paper**

Robust PCA in High-dimension: A Deterministic Approach

Jun 18, 2012

Jiashi Feng, Huan Xu, Shuicheng Yan

Jun 18, 2012

Jiashi Feng, Huan Xu, Shuicheng Yan

* ICML2012

**Click to Read Paper**

Closed-Form Solutions to A Category of Nuclear Norm Minimization Problems

Nov 23, 2010

Guangcan Liu, Ju Sun, Shuicheng Yan

It is an efficient and effective strategy to utilize the nuclear norm approximation to learn low-rank matrices, which arise frequently in machine learning and computer vision. So the exploration of nuclear norm minimization problems is gaining much attention recently. In this paper we shall prove that the following Low-Rank Representation (LRR) \cite{icml_2010_lrr,lrr_extention} problem: {eqnarray*} \min_{Z} \norm{Z}_*, & {s.t.,} & X=AZ, {eqnarray*} has a unique and closed-form solution, where $X$ and $A$ are given matrices. The proof is based on proving a lemma that allows us to get closed-form solutions to a category of nuclear norm minimization problems.
Nov 23, 2010

Guangcan Liu, Ju Sun, Shuicheng Yan

* NIPS Workshop on Low-Rank Methods for Large-Scale Machine Learning, 2010

**Click to Read Paper**

Visual Processing by a Unified Schatten-$p$ Norm and $\ell_q$ Norm Regularized Principal Component Pursuit

Aug 20, 2016

Jing Wang, Meng Wang, Xuegang Hu, Shuicheng Yan

In this paper, we propose a non-convex formulation to recover the authentic structure from the corrupted real data. Typically, the specific structure is assumed to be low rank, which holds for a wide range of data, such as images and videos. Meanwhile, the corruption is assumed to be sparse. In the literature, such a problem is known as Robust Principal Component Analysis (RPCA), which usually recovers the low rank structure by approximating the rank function with a nuclear norm and penalizing the error by an $\ell_1$-norm. Although RPCA is a convex formulation and can be solved effectively, the introduced norms are not tight approximations, which may cause the solution to deviate from the authentic one. Therefore, we consider here a non-convex relaxation, consisting of a Schatten-$p$ norm and an $\ell_q$-norm that promote low rank and sparsity respectively. We derive a proximal iteratively reweighted algorithm (PIRA) to solve the problem. Our algorithm is based on an alternating direction method of multipliers, where in each iteration we linearize the underlying objective function that allows us to have a closed form solution. We demonstrate that solutions produced by the linearized approximation always converge and have a tighter approximation than the convex counterpart. Experimental results on benchmarks show encouraging results of our approach.
Aug 20, 2016

Jing Wang, Meng Wang, Xuegang Hu, Shuicheng Yan

* Pattern Recognition, 2015

**Click to Read Paper**

Simultaneous Feature Learning and Hash Coding with Deep Neural Networks

Apr 14, 2015

Hanjiang Lai, Yan Pan, Ye Liu, Shuicheng Yan

Apr 14, 2015

Hanjiang Lai, Yan Pan, Ye Liu, Shuicheng Yan

* This paper has been accepted to IEEE International Conference on Pattern Recognition and Computer Vision (CVPR), 2015

**Click to Read Paper**

Revealing Cluster Structure of Graph by Path Following Replicator Dynamic

Mar 11, 2013

Hairong Liu, Longin Jan Latecki, Shuicheng Yan

Mar 11, 2013

Hairong Liu, Longin Jan Latecki, Shuicheng Yan

**Click to Read Paper**

Exact Low Tubal Rank Tensor Recovery from Gaussian Measurements

Jun 07, 2018

Canyi Lu, Jiashi Feng, Zhouchen Lin, Shuicheng Yan

The recent proposed Tensor Nuclear Norm (TNN) [Lu et al., 2016; 2018a] is an interesting convex penalty induced by the tensor SVD [Kilmer and Martin, 2011]. It plays a similar role as the matrix nuclear norm which is the convex surrogate of the matrix rank. Considering that the TNN based Tensor Robust PCA [Lu et al., 2018a] is an elegant extension of Robust PCA with a similar tight recovery bound, it is natural to solve other low rank tensor recovery problems extended from the matrix cases. However, the extensions and proofs are generally tedious. The general atomic norm provides a unified view of low-complexity structures induced norms, e.g., the $\ell_1$-norm and nuclear norm. The sharp estimates of the required number of generic measurements for exact recovery based on the atomic norm are known in the literature. In this work, with a careful choice of the atomic set, we prove that TNN is a special atomic norm. Then by computing the Gaussian width of certain cone which is necessary for the sharp estimate, we achieve a simple bound for guaranteed low tubal rank tensor recovery from Gaussian measurements. Specifically, we show that by solving a TNN minimization problem, the underlying tensor of size $n_1\times n_2\times n_3$ with tubal rank $r$ can be exactly recovered when the given number of Gaussian measurements is $O(r(n_1+n_2-r)n_3)$. It is order optimal when comparing with the degrees of freedom $r(n_1+n_2-r)n_3$. Beyond the Gaussian mapping, we also give the recovery guarantee of tensor completion based on the uniform random mapping by TNN minimization. Numerical experiments verify our theoretical results.
Jun 07, 2018

Canyi Lu, Jiashi Feng, Zhouchen Lin, Shuicheng Yan

* International Joint Conference on Artificial Intelligence (IJCAI), 2018

**Click to Read Paper**

Generative Partition Networks for Multi-Person Pose Estimation

Nov 28, 2017

Xuecheng Nie, Jiashi Feng, Junliang Xing, Shuicheng Yan

Nov 28, 2017

Xuecheng Nie, Jiashi Feng, Junliang Xing, Shuicheng Yan

**Click to Read Paper**

Training Group Orthogonal Neural Networks with Privileged Information

Aug 18, 2017

Yunpeng Chen, Xiaojie Jin, Jiashi Feng, Shuicheng Yan

Aug 18, 2017

Yunpeng Chen, Xiaojie Jin, Jiashi Feng, Shuicheng Yan

* Proceedings of the IJCAI-17

**Click to Read Paper**

More is Less: A More Complicated Network with Less Inference Complexity

May 15, 2017

Xuanyi Dong, Junshi Huang, Yi Yang, Shuicheng Yan

May 15, 2017

Xuanyi Dong, Junshi Huang, Yi Yang, Shuicheng Yan

* This paper has been accepted by the IEEE CVPR 2017

**Click to Read Paper**

Training Skinny Deep Neural Networks with Iterative Hard Thresholding Methods

Jul 19, 2016

Xiaojie Jin, Xiaotong Yuan, Jiashi Feng, Shuicheng Yan

Jul 19, 2016

Xiaojie Jin, Xiaotong Yuan, Jiashi Feng, Shuicheng Yan

**Click to Read Paper**

Fast Proximal Linearized Alternating Direction Method of Multiplier with Parallel Splitting

Nov 14, 2015

Canyi Lu, Huan Li, Zhouchen Lin, Shuicheng Yan

Nov 14, 2015

Canyi Lu, Huan Li, Zhouchen Lin, Shuicheng Yan

* AAAI 2016

**Click to Read Paper**