Search Results for author: Xin Du

Found 29 papers, 9 papers with code

Frequency-dependent Switching Control for Disturbance Attenuation of Linear Systems

no code implementations1 Jun 2023 Jingjing Zhang, Jan Heiland, Peter Benner, Xin Du

We show that our FDSC scheme is capable to approximate the solid in-band performance while maintaining acceptable out-of-band performance with regard to global time horizons as well as localized time horizons.

Physical-layer Adversarial Robustness for Deep Learning-based Semantic Communications

no code implementations12 May 2023 Guoshun Nan, Zhichun Li, Jinli Zhai, Qimei Cui, Gong Chen, Xin Du, Xuefei Zhang, Xiaofeng Tao, Zhu Han, Tony Q. S. Quek

We argue that central to the success of ESC is the robust interpretation of conveyed semantics at the receiver side, especially for security-critical applications such as automatic driving and smart healthcare.

Adversarial Robustness

Cross-Modal Retrieval for Motion and Text via MildTriple Loss

1 code implementation7 May 2023 Sheng Yan, Haoqiang Wang, Xin Du, Mengyuan Liu, Hong Liu

Previous work on motion data modeling mainly relied on autoregressive feature extractors that may forget previous information, while we propose an innovative model that includes simple yet powerful transformer-based motion and text encoders, which can learn representations from the two different modalities and capture long-term dependencies.

Cross-Modal Retrieval Retrieval +1

Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration

no code implementations22 Apr 2023 Peng Chen, Xin Du, Zhihui Lu, Hongfeng Chai

To this end, we define a threat model for backdoor attacks in VFL and introduce a universal adversarial backdoor (UAB) attack to poison the predictions of VFL.

Binary Classification Federated Learning

Frequency-limited H$_2$ Model Order Reduction Based on Relative Error

no code implementations20 Dec 2022 Umair Zulfiqar, Xin Du, Qiuyan Song, Zhi-Hua Xiao, Victor Sreeram

A small absolute error can be a misleading notion of accuracy when the original and reduced systems' responses are inherently small within the desired frequency interval.

Relative Error-based Time-limited H2 Model Order Reduction via Oblique Projection

no code implementations16 Dec 2022 Umair Zulfiqar, Xin Du, Qiuyan Song, Zhi-Hua Xiao, Victor Sreeram

Inspired by these conditions, an oblique projection algorithm is proposed that ensures small H2-norm relative error within the desired time interval.

ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning

no code implementations10 Nov 2022 Yang Zhou, Yuda Song, Hui Qian, Xin Du

Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks.

Image Restoration

Rethinking Performance Gains in Image Dehazing Networks

1 code implementation23 Sep 2022 Yuda Song, Yang Zhou, Hui Qian, Xin Du

Image dehazing is an active topic in low-level vision, and many image dehazing networks have been proposed with the rapid development of deep learning.

Image Dehazing Single Image Dehazing

Modular Degradation Simulation and Restoration for Under-Display Camera

1 code implementation23 Sep 2022 Yang Zhou, Yuda Song, Xin Du

Together with a pixel-wise discriminator and supervised loss, we can train the generator to simulate the UDC imaging degradation process.

Image Restoration

Risk-Driven Design of Perception Systems

1 code implementation21 May 2022 Anthony L. Corso, Sydney M. Katz, Craig Innes, Xin Du, Subramanian Ramamoorthy, Mykel J. Kochenderfer

We formulate a risk function to quantify the effect of a given perceptual error on overall safety, and show how we can use it to design safer perception systems by including a risk-dependent term in the loss function and generating training data in risk-sensitive regions.

NLOS Error Mitigation Using Weighted Least Squares and Kalman Filter in UWB Positioning

no code implementations12 May 2022 Ruixin Fan, Xin Du

In this letter, we propose the Weighted-Least-Squares Robust Kalman Filter (WLS-RKF) for NLOS identification and mitigation.

Vision Transformers for Single Image Dehazing

1 code implementation8 Apr 2022 Yuda Song, Zhuqing He, Hui Qian, Xin Du

Image dehazing is a representative low-level vision task that estimates latent haze-free images from hazy images.

Image Dehazing Single Image Dehazing

Multi-Curve Translator for High-Resolution Photorealistic Image Translation

1 code implementation15 Mar 2022 Yuda Song, Hui Qian, Xin Du

The dominant image-to-image translation methods are based on fully convolutional networks, which extract and translate an image's features and then reconstruct the image.

Image-to-Image Translation Vocal Bursts Intensity Prediction

Vision Checklist: Towards Testable Error Analysis of Image Models to Help System Designers Interrogate Model Capabilities

no code implementations27 Jan 2022 Xin Du, Benedicte Legastelois, Bhargavi Ganesh, Ajitha Rajan, Hana Chockler, Vaishak Belle, Stuart Anderson, Subramanian Ramamoorthy

Robustness evaluations like our checklist will be crucial in future safety evaluations of visual perception modules, and be useful for a wide range of stakeholders including designers, deployers, and regulators involved in the certification of these systems.

Autonomous Driving

DPVI: A Dynamic-Weight Particle-Based Variational Inference Framework

no code implementations2 Dec 2021 Chao Zhang, Zhijian Li, Hui Qian, Xin Du

We develop a general Dynamic-weight Particle-based Variational Inference (DPVI) framework according to a novel continuous composite flow, which evolves the positions and weights of particles simultaneously.

Variational Inference

Beyond Discriminant Patterns: On the Robustness of Decision Rule Ensembles

no code implementations21 Sep 2021 Xin Du, Subramanian Ramamoorthy, Wouter Duivesteijn, Jin Tian, Mykola Pechenizkiy

Specifically, we propose to leverage causal knowledge by regarding the distributional shifts in subpopulations and deployment environments as the results of interventions on the underlying system.

StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement

1 code implementation ICCV 2021 Yuda Song, Hui Qian, Xin Du

To make the method more practical, we propose a well-designed enhancer that can process a 4K-resolution image over 200 FPS but surpasses the contemporaneous single style image enhancement methods in terms of PSNR, SSIM, and LPIPS.

Image Enhancement

On frequency- and time-limited H2-optimal model order reduction

no code implementations6 Feb 2021 Umair Zulfiqar, Victor Sreeram, Xin Du

Moreover, stationary point iteration algorithms that satisfy two out of three necessary conditions for the local minimizer are also proposed.

Frequency-weighted H2-optimal model order reduction via oblique projection

no code implementations17 Jan 2021 Umair Zulfiqar, Victor Sreeram, Mian Ilyas Ahmad, Xin Du

In this paper, a projection-based model order reduction algorithm is proposed that constructs reduced-order models that nearly satisfy the first-order optimality conditions for the frequency-weighted H2-optimal model order reduction problem.

Iterative Rational Krylov Algorithms for model reduction of a class of constrained structural dynamic system with Engineering applications

no code implementations8 Jan 2021 Xin Du, M. Monir Uddiny, A. Mostakim Fonyz, Md. Tanzim Hossainx, Md. Nazmul Islam Shuzan

This paper discusses model order reduction of large sparse second-order index-3 differential algebraic equations (DAEs) by applying Iterative Rational Krylov Algorithm (IRKA).

Optimization and Control Computational Engineering, Finance, and Science Dynamical Systems

A Novel Framework with Information Fusion and Neighborhood Enhancement for User Identity Linkage

1 code implementation16 Mar 2020 Siyuan Chen, Jiahai Wang, Xin Du, Yanqing Hu

The information fusion component adopts a group of encoders and decoders to fuse heterogeneous information and generate discriminative node embeddings for preliminary matching.

Causal Discovery from Incomplete Data: A Deep Learning Approach

no code implementations15 Jan 2020 Yuhao Wang, Vlado Menkovski, Hao Wang, Xin Du, Mykola Pechenizkiy

As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs.

Causal Discovery Imputation

Adaptive Frequency-limited H2-Model Order Reduction

no code implementations26 Nov 2019 Umair Zulfiqar, Victor Sreeram, Xin Du

In this paper, we present an adaptive framework for constructing a pseudo-optimal reduced model for the frequency-limited H2-optimal model order reduction problem.

Adversarial Balancing-based Representation Learning for Causal Effect Inference with Observational Data

1 code implementation30 Apr 2019 Xin Du, Lei Sun, Wouter Duivesteijn, Alexander Nikolaev, Mykola Pechenizkiy

The challenges for this problem are two-fold: on the one hand, we have to derive a causal estimator to estimate the causal quantity from observational data, where there exists confounding bias; on the other hand, we have to deal with the identification of CATE when the distribution of covariates in treatment and control groups are imbalanced.

Causal Inference Representation Learning +2

struc2gauss: Structural Role Preserving Network Embedding via Gaussian Embedding

no code implementations25 May 2018 Yulong Pei, Xin Du, Jianpeng Zhang, George Fletcher, Mykola Pechenizkiy

Almost all previous methods represent a node into a point in space and focus on local structural information, i. e., neighborhood information.

Network Embedding

Semi-supervised structured output prediction by local linear regression and sub-gradient descent

no code implementations7 Jun 2016 Ru-Ze Liang, Wei Xie, Weizhi Li, Xin Du, Jim Jing-Yan Wang, Jingbin Wang

The existing semi-supervise structured output prediction methods learn a global predictor for all the data points in a data set, which ignores the differences of local distributions of the data set, and the effects to the structured output prediction.

regression Structured Prediction

Semi-supervised learning of local structured output predictors

no code implementations11 Apr 2016 Xin Du

In this paper, we study the problem of semi-supervised structured output prediction, which aims to learn predictors for structured outputs, such as sequences, tree nodes, vectors, etc., from a set of data points of both input-output pairs and single inputs without outputs.

Structured Prediction

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