Search Results for author: Xiao Li

Found 67 papers, 15 papers with code

BarrierNet: A Safety-Guaranteed Layer for Neural Networks

no code implementations22 Nov 2021 Wei Xiao, Ramin Hasani, Xiao Li, Daniela Rus

This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems.

Video Instance Segmentation by Instance Flow Assembly

no code implementations20 Oct 2021 Xiang Li, Jinglu Wang, Xiao Li, Yan Lu

Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes.

Instance Segmentation Object Localization +2

Convergence of Random Reshuffling Under The Kurdyka-Łojasiewicz Inequality

no code implementations10 Oct 2021 Xiao Li, Andre Milzarek, Junwen Qiu

Remarkably, we conduct convergence analysis for the non-descent RR with diminishing step sizes based on the KL inequality, which generalizes the standard KL analysis framework.

End-to-End Video Object Detection with Spatial-Temporal Transformers

no code implementations23 May 2021 Lu He, Qianyu Zhou, Xiangtai Li, Li Niu, Guangliang Cheng, Xiao Li, Wenxuan Liu, Yunhai Tong, Lizhuang Ma, Liqing Zhang

Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.

Optical Flow Estimation Video Object Detection

Attention-Based 3D Seismic Fault Segmentation Training by a Few 2D Slice Labels

no code implementations9 May 2021 YiMin Dou, Kewen Li, Jianbing Zhu, Xiao Li, Yingjie Xi

The task of image segmentation requires huge labels, especially 3D seismic data, which has a complex structure and lots of noise.

Fault Detection Semantic Segmentation

A Geometric Analysis of Neural Collapse with Unconstrained Features

1 code implementation NeurIPS 2021 Zhihui Zhu, Tianyu Ding, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu

In contrast to existing landscape analysis for deep neural networks which is often disconnected from practice, our analysis of the simplified model not only does it explain what kind of features are learned in the last layer, but it also shows why they can be efficiently optimized in the simplified settings, matching the empirical observations in practical deep network architectures.

Global Optimization

Out-of-Step Detection Based On an Improved Line Potential Energy Criterion

no code implementations14 Apr 2021 Xiao Li, Chongru Liu, Jin Ma

The line potential energy in the cutset is used as the criterion for monitoring the generator instability, but the criterion has the following two limitations due to narrowly defined conditions.

Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases

no code implementations3 Mar 2021 Xiao Huang, Di Zhu, Fan Zhang, Tao Liu, Xiao Li, Lei Zou

The rapid development of remote sensing techniques provides rich, large-coverage, and high-temporal information of the ground, which can be coupled with the emerging deep learning approaches that enable latent features and hidden geographical patterns to be extracted.

Model Selection

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

1 code implementation NeurIPS 2021 Sheng Liu, Xiao Li, Yuexiang Zhai, Chong You, Zhihui Zhu, Carlos Fernandez-Granda, Qing Qu

Furthermore, we show that convolutional normalization can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets.

The Logical Options Framework

no code implementations24 Feb 2021 Brandon Araki, Xiao Li, Kiran Vodrahalli, Jonathan DeCastro, Micah J. Fry, Daniela Rus

Learning composable policies for environments with complex rules and tasks is a challenging problem.

Hierarchical Reinforcement Learning

Provable Boolean Interaction Recovery from Tree Ensemble obtained via Random Forests

no code implementations23 Feb 2021 Merle Behr, Yu Wang, Xiao Li, Bin Yu

As a consequence, we show that RF yields consistent interaction discovery under the LSS model.

Statistics Theory Statistics Theory

Rethinking Natural Adversarial Examples for Classification Models

1 code implementation23 Feb 2021 Xiao Li, Jianmin Li, Ting Dai, Jie Shi, Jun Zhu, Xiaolin Hu

A detection model based on the classification model EfficientNet-B7 achieved a top-1 accuracy of 53. 95%, surpassing previous state-of-the-art classification models trained on ImageNet, suggesting that accurate localization information can significantly boost the performance of classification models on ImageNet-A.

Classification General Classification +1

Stability of 2D quantum many-body scar states against random disorder

no code implementations16 Feb 2021 Ke Huang, Yu Wang, Xiao Li

Recently a class of quantum systems exhibiting weak ergodicity breaking has attracted much attention.

Disordered Systems and Neural Networks Statistical Mechanics

Hybrid Beamforming for mmWave MU-MISO Systems Exploiting Multi-agent Deep Reinforcement Learning

no code implementations1 Feb 2021 Qisheng Wang, Xiao Li, Shi Jin, Yijiain Chen

In this letter, we investigate the hybrid beamforming based on deep reinforcement learning (DRL) for millimeter Wave (mmWave) multi-user (MU) multiple-input-single-output (MISO) system.

Fooling thermal infrared pedestrian detectors in real world using small bulbs

no code implementations20 Jan 2021 Xiaopei Zhu, Xiao Li, Jianmin Li, Zheyao Wang, Xiaolin Hu

We propose a physical attack method with small bulbs on a board against the state of-the-art pedestrian detectors.

Autonomous Driving

TSQA: Tabular Scenario Based Question Answering

1 code implementation14 Jan 2021 Xiao Li, Yawei Sun, Gong Cheng

To solve the task, we extend state-of-the-art MRC methods with TTGen, a novel table-to-text generator.

Machine Reading Comprehension Question Answering

A Bayesian Nonparametric model for textural pattern heterogeneity

1 code implementation11 Nov 2020 Xiao Li, Michele Guindani, Chaan S. Ng, Brian P. Hobbs

Cancer radiomics is an emerging discipline promising to elucidate lesion phenotypes and tumor heterogeneity through patterns of enhancement, texture, morphology, and shape.

Applications

Integrated Communication and Localization in mmWave Systems

no code implementations28 Sep 2020 Jie Yang, Jing Xu, Xiao Li, Shi Jin, Bo Gao

As the fifth-generation (5G) mobile communication system is being commercialized, extensive studies on the evolution of 5G and sixth-generation mobile communication systems have been conducted.

A Blockchain Transaction Graph based Machine Learning Method for Bitcoin Price Prediction

no code implementations21 Aug 2020 Xiao Li, Weili Wu

Bitcoin, as one of the most popular cryptocurrency, is recently attracting much attention of investors.

Feature Engineering

Multi-Task Neural Model for Agglutinative Language Translation

no code implementations ACL 2020 Yirong Pan, Xiao Li, Yating Yang, Rui Dong

Neural machine translation (NMT) has achieved impressive performance recently by using large-scale parallel corpora.

Machine Translation Translation

Distribution Aligned Multimodal and Multi-Domain Image Stylization

no code implementations2 Jun 2020 Minxuan Lin, Fan Tang, Wei-Ming Dong, Xiao Li, Chongyang Ma, Changsheng Xu

Currently, there are few methods that can perform both multimodal and multi-domain stylization simultaneously.

Image Stylization

A Text Reassembling Approach to Natural Language Generation

no code implementations16 May 2020 Xiao Li, Kees Van Deemter, Chenghua Lin

Recent years have seen a number of proposals for performing Natural Language Generation (NLG) based in large part on statistical techniques.

Text Generation

Curating a COVID-19 data repository and forecasting county-level death counts in the United States

1 code implementation16 May 2020 Nick Altieri, Rebecca L. Barter, James Duncan, Raaz Dwivedi, Karl Kumbier, Xiao Li, Robert Netzorg, Briton Park, Chandan Singh, Yan Shuo Tan, Tiffany Tang, Yu Wang, Chao Zhang, Bin Yu

We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.

COVID-19 Tracking Decision Making +2

An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety

no code implementations30 Apr 2020 Jing Han, Kun Qian, Meishu Song, Zijiang Yang, Zhao Ren, Shuo Liu, Juan Liu, Huaiyuan Zheng, Wei Ji, Tomoya Koike, Xiao Li, Zixing Zhang, Yoshiharu Yamamoto, Björn W. Schuller

In particular, by analysing speech recordings from these patients, we construct audio-only-based models to automatically categorise the health state of patients from four aspects, including the severity of illness, sleep quality, fatigue, and anxiety.

Sleep Quality

Deep Reinforcement Learning for Adaptive Learning Systems

no code implementations17 Apr 2020 Xiao Li, Hanchen Xu, Jinming Zhang, Hua-hua Chang

In this paper, we formulate the adaptive learning problem---the problem of how to find an individualized learning plan (called policy) that chooses the most appropriate learning materials based on learner's latent traits---faced in adaptive learning systems as a Markov decision process (MDP).

Q-Learning

COVID-19 and Computer Audition: An Overview on What Speech & Sound Analysis Could Contribute in the SARS-CoV-2 Corona Crisis

no code implementations24 Mar 2020 Björn W. Schuller, Dagmar M. Schuller, Kun Qian, Juan Liu, Huaiyuan Zheng, Xiao Li

We come to the conclusion that CA appears ready for implementation of (pre-)diagnosis and monitoring tools, and more generally provides rich and significant, yet so far untapped potential in the fight against COVID-19 spread.

Finding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications

no code implementations20 Jan 2020 Qing Qu, Zhihui Zhu, Xiao Li, Manolis C. Tsakiris, John Wright, René Vidal

The problem of finding the sparsest vector (direction) in a low dimensional subspace can be considered as a homogeneous variant of the sparse recovery problem, which finds applications in robust subspace recovery, dictionary learning, sparse blind deconvolution, and many other problems in signal processing and machine learning.

Dictionary Learning Representation Learning

Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation

no code implementations2 Jan 2020 Yirong Pan, Xiao Li, Yating Yang, Rui Dong

Experimental results show that our morphologically motivated word segmentation method is better suitable for the NMT model, which achieves significant improvements on Turkish-English and Uyghur-Chinese machine translation tasks on account of reducing data sparseness and language complexity.

Machine Translation Translation

MIMO Transmission through Reconfigurable Intelligent Surface: System Design, Analysis, and Implementation

no code implementations20 Dec 2019 Wankai Tang, Jun Yan Dai, Ming Zheng Chen, Kai-Kit Wong, Xiao Li, Xinsheng Zhao, Shi Jin, Qiang Cheng, Tie Jun Cui

Reconfigurable intelligent surface (RIS) is a new paradigm that has great potential to achieve cost-effective, energy-efficient information modulation for wireless transmission, by the ability to change the reflection coefficients of the unit cells of a programmable metasurface.

Analysis of the Optimization Landscapes for Overcomplete Representation Learning

no code implementations5 Dec 2019 Qing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang, Zhihui Zhu

In this work, we show these problems can be formulated as $\ell^4$-norm optimization problems with spherical constraint, and study the geometric properties of their nonconvex optimization landscapes.

Global Optimization Representation Learning

A Stable Variational Autoencoder for Text Modelling

1 code implementation WS 2019 Ruizhe Li, Xiao Li, Chenghua Lin, Matthew Collinson, Rui Mao

Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data.

Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods

1 code implementation12 Nov 2019 Xiao Li, Shixiang Chen, Zengde Deng, Qing Qu, Zhihui Zhu, Anthony Man Cho So

To the best of our knowledge, these are the first convergence guarantees for using Riemannian subgradient-type methods to optimize a class of nonconvex nonsmooth functions over the Stiefel manifold.

Dictionary Learning

Physical Layer Security Enhancement Exploiting Intelligent Reflecting Surface

no code implementations7 Nov 2019 Keming Feng, Xiao Li, Yu Han, Shi Jin, Yijian Chen

In this letter, the use of intelligent reflecting surface (IRS) to enhance the physical layer security of downlink wireless communication is investigated.

A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution

1 code implementation NeurIPS 2019 Qing Qu, Xiao Li, Zhihui Zhu

We study the multi-channel sparse blind deconvolution (MCS-BD) problem, whose task is to simultaneously recover a kernel $\mathbf a$ and multiple sparse inputs $\{\mathbf x_i\}_{i=1}^p$ from their circulant convolution $\mathbf y_i = \mathbf a \circledast \mathbf x_i $ ($i=1,\cdots, p$).

PrecoderNet: Hybrid Beamforming for Millimeter Wave Systems with Deep Reinforcement Learning

no code implementations31 Jul 2019 Qisheng Wang, Keming Feng, Xiao Li, Shi Jin

In this letter, we investigate the hybrid beamforming for millimeter wave massive multiple-input multiple-output (MIMO) system based on deep reinforcement learning (DRL).

Latent Space Factorisation and Manipulation via Matrix Subspace Projection

1 code implementation ICML 2020 Xiao Li, Chenghua Lin, Ruizhe Li, Chaozheng Wang, Frank Guerin

We demonstrate the utility of our method for attribute manipulation in autoencoders trained across varied domains, using both human evaluation and automated methods.

Ranked #3 on Image Generation on CelebA 256x256 (FID metric)

Face Generation Face Swapping

A Debiased MDI Feature Importance Measure for Random Forests

3 code implementations NeurIPS 2019 Xiao Li, Yu Wang, Sumanta Basu, Karl Kumbier, Bin Yu

Based on the original definition of MDI by Breiman et al. for a single tree, we derive a tight non-asymptotic bound on the expected bias of MDI importance of noisy features, showing that deep trees have higher (expected) feature selection bias than shallow ones.

Feature Importance Feature Selection +1

Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks

no code implementations CVPR 2019 Xiao Li, Yue Dong, Pieter Peers, Xin Tong

Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes.

Automata Guided Skill Composition

no code implementations ICLR 2019 Xiao Li, Yao Ma, Calin Belta

Skills learned through (deep) reinforcement learning often generalizes poorly across tasks and re-training is necessary when presented with a new task.

Arbitrage of Energy Storage in Electricity Markets with Deep Reinforcement Learning

no code implementations28 Apr 2019 Hanchen Xu, Xiao Li, Xiangyu Zhang, Junbo Zhang

In this letter, we address the problem of controlling energy storage systems (ESSs) for arbitrage in real-time electricity markets under price uncertainty.

Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing

no code implementations27 Mar 2019 Jun Gao, Xiao Li, Li-Wei Wang, Sanja Fidler, Stephen Lin

We present a method for compositing virtual objects into a photograph such that the object colors appear to have been processed by the photo's camera imaging pipeline.

Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization

no code implementations NeurIPS 2018 Zhihui Zhu, Xiao Li, Kai Liu, Qiuwei Li

Symmetric nonnegative matrix factorization (NMF), a special but important class of the general NMF, is demonstrated to be useful for data analysis and in particular for various clustering tasks.

Image Clustering

Statistical NLG for Generating the Content and Form of Referring Expressions

no code implementations WS 2018 Xiao Li, Kees Van Deemter, Chenghua Lin

This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully.

Referring expression generation Text Generation

Optimal Hierarchical Learning Path Design with Reinforcement Learning

no code implementations12 Oct 2018 Xiao Li, Hanchen Xu, Jinming Zhang, Hua-hua Chang

To this end, we first develop a model for students' hierarchical skills in the E-learning system.

Hierarchical structure

Nonconvex Robust Low-rank Matrix Recovery

no code implementations24 Sep 2018 Xiao Li, Zhihui Zhu, Anthony Man-Cho So, Rene Vidal

In this paper we study the problem of recovering a low-rank matrix from a number of random linear measurements that are corrupted by outliers taking arbitrary values.

Information Theory Information Theory

Automata Guided Reinforcement Learning With Demonstrations

no code implementations17 Sep 2018 Xiao Li, Yao Ma, Calin Belta

Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals.

Hierarchical structure Temporal Logic

AUTOMATA GUIDED HIERARCHICAL REINFORCEMENT LEARNING FOR ZERO-SHOT SKILL COMPOSITION

no code implementations ICLR 2018 Xiao Li, Yao Ma, Calin Belta

An obstacle that prevents the wide adoption of (deep) reinforcement learning (RL) in control systems is its need for a large number of interactions with the environment in order to master a skill.

Hierarchical Reinforcement Learning

Automata-Guided Hierarchical Reinforcement Learning for Skill Composition

no code implementations31 Oct 2017 Xiao Li, Yao Ma, Calin Belta

Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task.

Hierarchical Reinforcement Learning

A Policy Search Method For Temporal Logic Specified Reinforcement Learning Tasks

no code implementations27 Sep 2017 Xiao Li, Yao Ma, Calin Belta

In this paper, we explore the use of temporal logic (TL) to specify tasks in reinforcement learning.

Temporal Logic

Optimized Structured Sparse Sensing Matrices for Compressive Sensing

no code implementations19 Sep 2017 Tao Hong, Xiao Li, Zhihui Zhu, Qiuwei Li

We consider designing a robust structured sparse sensing matrix consisting of a sparse matrix with a few non-zero entries per row and a dense base matrix for capturing signals efficiently We design the robust structured sparse sensing matrix through minimizing the distance between the Gram matrix of the equivalent dictionary and the target Gram of matrix holding small mutual coherence.

Compressive Sensing Image Compression

Investigating the content and form of referring expressions in Mandarin: introducing the Mtuna corpus

no code implementations WS 2017 Kees van Deemter, Le Sun, Rint Sybesma, Xiao Li, Bo Chen, Muyun Yang

East Asian languages are thought to handle reference differently from languages such as English, particularly in terms of the marking of definiteness and number.

Text Generation

Log-linear Models for Uyghur Segmentation in Spoken Language Translation

no code implementations RANLP 2017 Chenggang Mi, Yating Yang, Rui Dong, Xi Zhou, Lei Wang, Xiao Li, Tonghai Jiang

To alleviate data sparsity in spoken Uyghur machine translation, we proposed a log-linear based morphological segmentation approach.

Machine Translation Translation +1

Reinforcement Learning With Temporal Logic Rewards

no code implementations11 Dec 2016 Xiao Li, Cristian-Ioan Vasile, Calin Belta

We propose Truncated Linear Temporal Logic (TLTL) as specifications language, that is arguably well suited for the robotics applications, together with quantitative semantics, i. e., robustness degree.

Temporal Logic

A Hierarchical Reinforcement Learning Method for Persistent Time-Sensitive Tasks

no code implementations20 Jun 2016 Xiao Li, Calin Belta

Reinforcement learning has been applied to many interesting problems such as the famous TD-gammon and the inverted helicopter flight.

Hierarchical Reinforcement Learning Temporal Logic

An Active Learning Framework using Sparse-Graph Codes for Sparse Polynomials and Graph Sketching

no code implementations NeurIPS 2015 Xiao Li, Kannan Ramchandran

By writing the cut function as a polynomial and exploiting the graph structure, we propose a sketching algorithm to learn the an arbitrary $n$-node unknown graph using only few cut queries, which scales {\it almost linearly} in the number of edges and {\it sub-linearly} in the graph size $n$.

Active Learning

SPRIGHT: A Fast and Robust Framework for Sparse Walsh-Hadamard Transform

2 code implementations26 Aug 2015 Xiao Li, Joseph K. Bradley, Sameer Pawar, Kannan Ramchandran

We consider the problem of computing the Walsh-Hadamard Transform (WHT) of some $N$-length input vector in the presence of noise, where the $N$-point Walsh spectrum is $K$-sparse with $K = {O}(N^{\delta})$ scaling sub-linearly in the input dimension $N$ for some $0<\delta<1$.

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