Search Results for author: Xiaolin Huang

Found 48 papers, 14 papers with code

Subspace Adversarial Training

no code implementations24 Nov 2021 Tao Li, Yingwen Wu, Sizhe Chen, Kun Fang, Xiaolin Huang

To control the growth of the gradient during the training, we propose a new AT method, subspace adversarial training (Sub-AT), which constrains the AT in a carefully extracted subspace.

Semi-tensor Product-based TensorDecomposition for Neural Network Compression

no code implementations30 Sep 2021 Hengling Zhao, Yipeng Liu, Xiaolin Huang, Ce Zhu

Tucker decomposition, Tensor Train (TT) and Tensor Ring (TR) are common decomposition for low rank compression of deep neural networks.

Low-rank compression Neural Network Compression +1

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing

1 code implementation15 Jul 2021 Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Michael Ng

The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications.

image smoothing

Adaptive Feature Alignment for Adversarial Training

no code implementations31 May 2021 Tao Wang, Ruixin Zhang, Xingyu Chen, Kai Zhao, Xiaolin Huang, Yuge Huang, Shaoxin Li, Jilin Li, Feiyue Huang

Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths.

Adversarial Defense

QueryNet: Attack by Multi-Identity Surrogates

1 code implementation31 May 2021 Sizhe Chen, Zhehao Huang, Qinghua Tao, Xiaolin Huang

Deep Neural Networks (DNNs) are acknowledged as vulnerable to adversarial attacks, while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates.

Dominant Patterns: Critical Features Hidden in Deep Neural Networks

no code implementations31 May 2021 Zhixing Ye, Shaofei Qin, Sizhe Chen, Xiaolin Huang

As the name suggests, for a natural image, if we add the dominant pattern of a DNN to it, the output of this DNN is determined by the dominant pattern instead of the original image, i. e., DNN's prediction is the same with the dominant pattern's.

Residual Enhanced Multi-Hypergraph Neural Network

1 code implementation2 May 2021 Jing Huang, Xiaolin Huang, Jie Yang

Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various research domains.

Representation Learning

Towards Unbiased Random Features with Lower Variance For Stationary Indefinite Kernels

1 code implementation13 Apr 2021 Qin Luo, Kun Fang, Jie Yang, Xiaolin Huang

Random Fourier Features (RFF) demonstrate wellappreciated performance in kernel approximation for largescale situations but restrict kernels to be stationary and positive definite.

Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel

1 code implementation22 Mar 2021 Lei Tan, Shutong Wu, Xiaolin Huang

In this paper, we introduce the Weighted Neural Tangent Kernel (WNTK), a generalized and improved tool, which can capture an over-parameterized NN's training dynamics under different optimizers.

Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces

1 code implementation20 Mar 2021 Tao Li, Lei Tan, Qinghua Tao, Yipeng Liu, Xiaolin Huang

Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the DNNs could be trained in low-dimensional subspaces.

Dimensionality Reduction

Measuring $\ell_\infty$ Attacks by the $\ell_2$ Norm

no code implementations20 Feb 2021 Sizhe Chen, Qinghua Tao, Zhixing Ye, Xiaolin Huang

Deep Neural Networks (DNNs) could be easily fooled by Adversarial Examples (AEs) with the imperceptible difference to original samples in human eyes.

Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT

no code implementations10 Dec 2020 Yulei Qin, Hao Zheng, Yun Gu, Xiaolin Huang, Jie Yang, Lihui Wang, Feng Yao, Yue-Min Zhu, Guang-Zhong Yang

Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background.

Representation Learning

Towards a Unified Quadrature Framework for Large-Scale Kernel Machines

no code implementations3 Nov 2020 Fanghui Liu, Xiaolin Huang, Yudong Chen, Johan A. K. Suykens

In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical integration representation.

Numerical Integration

Towards Robust Neural Networks via Orthogonal Diversity

1 code implementation23 Oct 2020 Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Jia Cai, Feipeng Cai, Xiaolin Huang, Jie Yang

Despite of the efficiency on defending specific attacks, adversarial training essentially benefits from the data augmentation, but does not contribute to the robustness of DNN itself, and usually suffers accuracy drop on clean data as well as inefficiency on unknown attacks.

Adversarial Robustness Data Augmentation

One-shot Distributed Algorithm for Generalized Eigenvalue Problem

no code implementations22 Oct 2020 Kexin Lv, Fan He, Xiaolin Huang, Jie Yang, Liming Chen

Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy.

Learn Robust Features via Orthogonal Multi-Path

no code implementations28 Sep 2020 Kun Fang, Xiaolin Huang, Yingwen Wu, Tao Li, Jie Yang

To defend adversarial attacks, we design a block containing multiple paths to learn robust features and the parameters of these paths are required to be orthogonal with each other.

End-to-end Kernel Learning via Generative Random Fourier Features

no code implementations10 Sep 2020 Kun Fang, Xiaolin Huang, Fanghui Liu, Jie Yang

In the second-stage process, a linear learner is conducted with respect to the mapped random features.

Adversarial Robustness

Relevance Attack on Detectors

1 code implementation16 Aug 2020 Sizhe Chen, Fan He, Xiaolin Huang, Kun Zhang

This paper focuses on high-transferable adversarial attacks on detectors, which are hard to attack in a black-box manner, because of their multiple-output characteristics and the diversity across architectures.

Autonomous Driving Instance Segmentation +2

Analysis of Regularized Least Squares in Reproducing Kernel Krein Spaces

no code implementations1 Jun 2020 Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens

In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS).

Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures

no code implementations30 May 2020 Fanghui Liu, Xiaolin Huang, Yingyi Chen, Johan A. K. Suykens

In this paper, we attempt to solve a long-lasting open question for non-positive definite (non-PD) kernels in machine learning community: can a given non-PD kernel be decomposed into the difference of two PD kernels (termed as positive decomposition)?

One-shot Distibuted Algorithm for PCA with RBF Kernels

1 code implementation6 May 2020 Fan He, Kexin Lv, Jie Yang, Xiaolin Huang

This letter proposes a one-shot algorithm for feature-distributed kernel PCA.

Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond

no code implementations23 Apr 2020 Fanghui Liu, Xiaolin Huang, Yudong Chen, Johan A. K. Suykens

This survey may serve as a gentle introduction to this topic, and as a users' guide for practitioners interested in applying the representative algorithms and understanding theoretical results under various technical assumptions.

Sparse Generalized Canonical Correlation Analysis: Distributed Alternating Iteration based Approach

no code implementations23 Apr 2020 Jia Cai, Kexin Lv, Junyi Huo, Xiaolin Huang, Jie Yang

To overcome this limitation, in this paper, we propose a sparse generalized canonical correlation analysis (GCCA), which could detect the latent relations of multiview data with sparse structures.

Adversarial Imitation Attack

no code implementations28 Mar 2020 Mingyi Zhou, Jing Wu, Yipeng Liu, Xiaolin Huang, Shuaicheng Liu, Xiang Zhang, Ce Zhu

Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model.

Adversarial Attack

Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention

no code implementations19 Mar 2020 Tianyi Zhang, Yun Gu, Xiaolin Huang, Enmei Tu, Jie Yang

In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules.

Image Super-Resolution

Double Backpropagation for Training Autoencoders against Adversarial Attack

no code implementations4 Mar 2020 Chengjin Sun, Sizhe Chen, Xiaolin Huang

We restrict the gradient from the reconstruction image to the original one so that the autoencoder is not sensitive to trivial perturbation produced by the adversarial attack.

Adversarial Attack Robust classification

Type I Attack for Generative Models

no code implementations4 Mar 2020 Chengjin Sun, Sizhe Chen, Jia Cai, Xiaolin Huang

To implement the Type I attack, we destroy the original one by increasing the distance in input space while keeping the output similar because different inputs may correspond to similar features for the property of deep neural network.

HRFA: High-Resolution Feature-based Attack

1 code implementation21 Jan 2020 Zhixing Ye, Sizhe Chen, Peidong Zhang, Chengjin Sun, Xiaolin Huang

Adversarial attacks have long been developed for revealing the vulnerability of Deep Neural Networks (DNNs) by adding imperceptible perturbations to the input.

Denoising Face Verification

Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet

no code implementations16 Jan 2020 Sizhe Chen, Zhengbao He, Chengjin Sun, Jie Yang, Xiaolin Huang

AoA enjoys a significant increase in transferability when the traditional cross entropy loss is replaced with the attention loss.

Adversarial Attack

Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection

no code implementations29 Dec 2019 Tianshu Chu, Qin Luo, Jie Yang, Xiaolin Huang

In addition, the results also demonstrate that the higher-precision bottom layers could boost the 1-bit network performance appreciably due to a better preservation of the original image information while the lower-precision posterior layers contribute to the regularization of $k-$bit networks.

General Classification Image Classification +2

DAmageNet: A Universal Adversarial Dataset

1 code implementation16 Dec 2019 Sizhe Chen, Xiaolin Huang, Zhengbao He, Chengjin Sun

Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence.

Adversarial Attack

Random Fourier Features via Fast Surrogate Leverage Weighted Sampling

no code implementations20 Nov 2019 Fanghui Liu, Xiaolin Huang, Yudong Chen, Jie Yang, Johan A. K. Suykens

In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation.

Deep Kernel Learning via Random Fourier Features

no code implementations7 Oct 2019 Jiaxuan Xie, Fanghui Liu, Kaijie Wang, Xiaolin Huang

On small datasets (less than 1000 samples), for which deep learning is generally not suitable due to overfitting, our method achieves superior performance compared to advanced kernel methods.

Small Data Image Classification

Data Consistent Artifact Reduction for Limited Angle Tomography with Deep Learning Prior

no code implementations19 Aug 2019 Yixing Huang, Alexander Preuhs, Guenter Lauritsch, Michael Manhart, Xiaolin Huang, Andreas Maier

Robustness of deep learning methods for limited angle tomography is challenged by two major factors: a) due to insufficient training data the network may not generalize well to unseen data; b) deep learning methods are sensitive to noise.

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing

1 code implementation23 Jul 2019 Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Ian Reid

In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.

image smoothing

Robust Visual Tracking Revisited: From Correlation Filter to Template Matching

no code implementations15 Apr 2019 Fanghui Liu, Chen Gong, Xiaolin Huang, Tao Zhou, Jie Yang, DaCheng Tao

In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs).

Template Matching Visual Tracking

Online PCB Defect Detector On A New PCB Defect Dataset

1 code implementation17 Feb 2019 Sanli Tang, Fan He, Xiaolin Huang, Jie Yang

To train the deep model, a dataset is established, namely DeepPCB, which contains 1, 500 image pairs with annotations including positions of 6 common types of PCB defects.

Defect Detection

Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks

no code implementations13 Oct 2018 Yulei Qin, Juan Wen, Hao Zheng, Xiaolin Huang, Jie Yang, Ning Song, Yue-Min Zhu, Lingqian Wu, Guang-Zhong Yang

To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks.

General Classification Multi-Task Learning

Generalization Properties of hyper-RKHS and its Applications

no code implementations26 Sep 2018 Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens

This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view.

Learning Theory

Adversarial Attack Type I: Cheat Classifiers by Significant Changes

no code implementations3 Sep 2018 Sanli Tang, Xiaolin Huang, Mingjian Chen, Chengjin Sun, Jie Yang

Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations.

Adversarial Attack

Learning Data-adaptive Nonparametric Kernels

no code implementations31 Aug 2018 Fanghui Liu, Xiaolin Huang, Chen Gong, Jie Yang, Li Li

Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility.

Indefinite Kernel Logistic Regression with Concave-inexact-convex Procedure

no code implementations6 Jul 2017 Fanghui Liu, Xiaolin Huang, Chen Gong, Jie Yang, Johan A. K. Suykens

Since the concave-convex procedure has to solve a sub-problem in each iteration, we propose a concave-inexact-convex procedure (CCICP) algorithm with an inexact solving scheme to accelerate the solving process.

Nonconvex penalties with analytical solutions for one-bit compressive sensing

no code implementations4 Jun 2017 Xiaolin Huang, Ming Yan

For several nonconvex penalties, including minimax concave penalty (MCP), $\ell_0$ norm, and sorted $\ell_1$ penalty, we provide fast algorithms for finding the analytical solutions by solving the dual problem.

Compressive Sensing Learning Theory

Online Robust Principal Component Analysis with Change Point Detection

2 code implementations19 Feb 2017 Wei Xiao, Xiaolin Huang, Jorge Silva, Saba Emrani, Arin Chaudhuri

Robust PCA methods are typically batch algorithms which requires loading all observations into memory before processing.

Change Point Detection Two-sample testing

Mixed one-bit compressive sensing with applications to overexposure correction for CT reconstruction

no code implementations3 Jan 2017 Xiaolin Huang, Yan Xia, Lei Shi, Yixing Huang, Ming Yan, Joachim Hornegger, Andreas Maier

Aiming at overexposure correction for computed tomography (CT) reconstruction, we in this paper propose a mixed one-bit compressive sensing (M1bit-CS) to acquire information from both regular and saturated measurements.

Compressive Sensing Computed Tomography (CT) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.