Multiple Sclerosis Lesion Inpainting Using Non-Local Partial Convolutions

Dec 24, 2018

Hao Xiong, Dacheng Tao

Dec 24, 2018

Hao Xiong, Dacheng Tao

**Click to Read Paper**

Face detection is essential to facial analysis tasks such as facial reenactment and face recognition. Both cascade face detectors and anchor-based face detectors have translated shining demos into practice and received intensive attention from the community. However, cascade face detectors often suffer from a low detection accuracy, while anchor-based face detectors rely heavily on very large networks pre-trained on large scale image classification datasets such as ImageNet [1], which is not computationally efficient for both training and deployment. In this paper, we devise an efficient anchor-based cascade framework called anchor cascade. To improve the detection accuracy by exploring contextual information, we further propose a context pyramid maxout mechanism for anchor cascade. As a result, anchor cascade can train very efficient face detection models with a high detection accuracy. Specifically, comparing with a popular CNN-based cascade face detector MTCNN [2], our anchor cascade face detector greatly improves the detection accuracy, e.g., from 0.9435 to 0.9704 at 1k false positives on FDDB, while it still runs in comparable speed. Experimental results on two widely used face detection benchmarks, FDDB and WIDER FACE, demonstrate the effectiveness of the proposed framework.

**Click to Read Paper**
Variance Reduced methods for Non-convex Composition Optimization

Nov 13, 2017

Liu Liu, Ji Liu, Dacheng Tao

This paper explores the non-convex composition optimization in the form including inner and outer finite-sum functions with a large number of component functions. This problem arises in some important applications such as nonlinear embedding and reinforcement learning. Although existing approaches such as stochastic gradient descent (SGD) and stochastic variance reduced gradient (SVRG) descent can be applied to solve this problem, their query complexity tends to be high, especially when the number of inner component functions is large. In this paper, we apply the variance-reduced technique to derive two variance reduced algorithms that significantly improve the query complexity if the number of inner component functions is large. To the best of our knowledge, this is the first work that establishes the query complexity analysis for non-convex stochastic composition. Experiments validate the proposed algorithms and theoretical analysis.
Nov 13, 2017

Liu Liu, Ji Liu, Dacheng Tao

**Click to Read Paper**

Duality-free Methods for Stochastic Composition Optimization

Oct 26, 2017

Liu Liu, Ji Liu, Dacheng Tao

Oct 26, 2017

Liu Liu, Ji Liu, Dacheng Tao

**Click to Read Paper**

Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition

May 17, 2017

Changxing Ding, Dacheng Tao

May 17, 2017

Changxing Ding, Dacheng Tao

* Accepted Version to IEEE T-PAMI

**Click to Read Paper**

Real Time Fine-Grained Categorization with Accuracy and Interpretability

Oct 04, 2016

Shaoli Huang, Dacheng Tao

Oct 04, 2016

Shaoli Huang, Dacheng Tao

* arXiv admin note: text overlap with arXiv:1512.08086

**Click to Read Paper**

Variance-Reduced Proximal Stochastic Gradient Descent for Non-convex Composite optimization

Sep 11, 2016

Xiyu Yu, Dacheng Tao

Sep 11, 2016

Xiyu Yu, Dacheng Tao

* This paper has been withdrawn by the author due to an error in the proof of the convergence rate. They will modify this proof as soon as possible

**Click to Read Paper**

* final version, ACM Transactions on Intelligent Systems and Technology, 2016

**Click to Read Paper**

Robust Face Recognition via Multimodal Deep Face Representation

Sep 01, 2015

Changxing Ding, Dacheng Tao

Sep 01, 2015

Changxing Ding, Dacheng Tao

* To appear in IEEE Trans. Multimedia

**Click to Read Paper**

**Click to Read Paper**

* 53 pages, 17 figures

**Click to Read Paper**

**Click to Read Paper**

Unmixing Incoherent Structures of Big Data by Randomized or Greedy Decomposition

Sep 02, 2013

Tianyi Zhou, Dacheng Tao

Sep 02, 2013

Tianyi Zhou, Dacheng Tao

* 42 pages, 5 figures, 4 tables, 5 algorithms

**Click to Read Paper**

Asymptotic Generalization Bound of Fisher's Linear Discriminant Analysis

Apr 22, 2013

Wei Bian, Dacheng Tao

Apr 22, 2013

Wei Bian, Dacheng Tao

**Click to Read Paper**

**Click to Read Paper**

* 17 pages, 3 figures, technical report

**Click to Read Paper**

Multi-label Learning via Structured Decomposition and Group Sparsity

Mar 03, 2011

Tianyi Zhou, Dacheng Tao

Mar 03, 2011

Tianyi Zhou, Dacheng Tao

* 13 pages, 3 tables

**Click to Read Paper**

**Click to Read Paper**

**Click to Read Paper**

Theoretical Analysis of Adversarial Learning: A Minimax Approach

Nov 13, 2018

Zhuozhuo Tu, Jingwei Zhang, Dacheng Tao

We propose a general theoretical method for analyzing the risk bound in the presence of adversaries. In particular, we try to fit the adversarial learning problem into the minimax framework. We first show that the original adversarial learning problem could be reduced to a minimax statistical learning problem by introducing a transport map between distributions. Then we prove a risk bound for this minimax problem in terms of covering numbers. In contrast to previous minimax bounds in \cite{lee,far}, our bound is informative when the radius of the ambiguity set is small. Our method could be applied to multi-class classification problems and commonly-used loss functions such as hinge loss and ramp loss. As two illustrative examples, we derive the adversarial risk bounds for kernel-SVM and deep neural networks. Our results indicate that a stronger adversary might have a negative impact on the complexity of the hypothesis class and the existence of margin could serve as a defense mechanism to counter adversarial attacks.
Nov 13, 2018

Zhuozhuo Tu, Jingwei Zhang, Dacheng Tao

* 22 pages

**Click to Read Paper**