no code implementations • NeurIPS 2009 • Yiming Ying, Kai-Zhu Huang, Colin Campbell
From this saddle representation, we develop an efficient smooth optimization approach for sparse metric learning although the learning model is based on a non-differential loss function.
1 code implementation • 3 Jul 2012 • Yao Lu, Kai-Zhu Huang, Cheng-Lin Liu
In particular, with high accuracy, our algorithm takes only a few seconds (in a PC) to match two graphs of 1, 000 nodes.
no code implementations • 11 Jan 2013 • Xu-Cheng Yin, Xuwang Yin, Kai-Zhu Huang, Hong-Wei Hao
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks.
no code implementations • 19 Nov 2015 • Chunchuan Lyu, Kai-Zhu Huang, Hai-Ning Liang
In this paper, we propose a unified framework to build robust machine learning models against adversarial examples.
no code implementations • 16 May 2017 • Jimin Xiao, Yanchun Xie, Tammam Tillo, Kai-Zhu Huang, Yunchao Wei, Jiashi Feng
In addition, to relieve the negative effect caused by varying visual appearances of the same individual, IAN introduces a novel center loss that can increase the intra-class compactness of feature representations.
1 code implementation • 27 Oct 2017 • Xiao-Bo Jin, Xu-Yao Zhang, Kai-Zhu Huang, Guang-Gang Geng
Conjugate gradient (CG) methods are a class of important methods for solving linear equations and nonlinear optimization problems.
no code implementations • 16 Jul 2018 • Shufei Zhang, Kai-Zhu Huang, Jianke Zhu, Yang Liu
All the existing adversarial training methods consider only how the worst perturbed examples (i. e., adversarial examples) could affect the model output.
no code implementations • 30 Oct 2018 • Guoqiang Zhong, Xin Lin, Kang Chen, Qingyang Li, Kai-Zhu Huang
Attention is an important cognition process of humans, which helps humans concentrate on critical information during their perception and learning.
no code implementations • 8 Nov 2018 • Yanchun Xie, Jimin Xiao, Kai-Zhu Huang, Jeyarajan Thiyagalingam, Yao Zhao
In this paper, we propose a novel approach to address the correlation filter update problem.
no code implementations • 19 Nov 2018 • Xiao-Bo Jin, Kai-Zhu Huang, Jianyu Miao
AEEN-HOA consists of two branches, i. e., the upper stream is capable of erasing some initially discovered regions, then the high-order attribute supervision is incorporated to characterize the relationship between the class attributes.
no code implementations • 18 Jan 2019 • Zhuang Qian, Kai-Zhu Huang, Qiufeng Wang, Jimin Xiao, Rui Zhang
Generative Adversarial Networks (GAN) receive great attentions recently due to its excellent performance in image generation, transformation, and super-resolution.
no code implementations • ICLR 2019 • Shufei Zhang, Kai-Zhu Huang, Rui Zhang, Amir Hussain
In this paper, we propose a generalized framework that addresses the learning problem of adversarial examples with Riemannian geometry.
no code implementations • NAACL 2019 • Hang Dong, Wei Wang, Kai-Zhu Huang, Frans Coenen
To better utilise this information, we design a framework that separates the title from the content of a document and apply a title-guided attention mechanism over each sentence in the content.
1 code implementation • 27 Aug 2019 • Dingyuan Zheng, Jimin Xiao, Kai-Zhu Huang, Yao Zhao
Person search aims to search for a target person among multiple images recorded by multiple surveillance cameras, which faces various challenges from both pedestrian detection and person re-identification.
no code implementations • 15 Nov 2019 • Shufei Zhang, Kai-Zhu Huang, Zenglin Xu
We propose to exploit an energy function to describe the stability and prove that reducing such energy guarantees the robustness against adversarial examples.
1 code implementation • 19 Nov 2019 • Bingfeng Zhang, Jimin Xiao, Yunchao Wei, Ming-Jie Sun, Kai-Zhu Huang
Such reliable regions are then directly served as ground-truth labels for the parallel segmentation branch, where a newly designed dense energy loss function is adopted for optimization.
Ranked #22 on Semantic Segmentation on PASCAL VOC 2012 val
no code implementations • 20 Nov 2019 • Lirong He, Ziyi Guo, Kai-Zhu Huang, Zenglin Xu
In a worst-case scenario, MPM tries to minimize an upper bound of misclassification probabilities, considering the global information (i. e., mean and covariance information of each class).
1 code implementation • 11 Dec 2019 • Jiezhu Cheng, Kai-Zhu Huang, Zibin Zheng
Multivariate time series forecasting is an important yet challenging problem in machine learning.
no code implementations • 28 Dec 2019 • Fiseha B. Tesema, Hong Wu, Mingjian Chen, Junpeng Lin, William Zhu, Kai-Zhu Huang
When using a more advanced RPN in our framework, our approach can be further improved and get competitive results on both benchmarks.
no code implementations • ICLR 2020 • Shufei Zhang, Zhuang Qian, Kai-Zhu Huang, Jimin Xiao, Yuan He
Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations.
no code implementations • ECCV 2020 • Yanchun Xie, Jimin Xiao, Ming-Jie Sun, Chao Yao, Kai-Zhu Huang
To this end, we engaged neural texture transfer to swap texture features between the low-resolution image and the high-resolution reference image.