Search Results for author: Xiao Yang

Found 40 papers, 12 papers with code

Query2Label: A Simple Transformer Way to Multi-Label Classification

1 code implementation22 Jul 2021 Shilong Liu, Lei Zhang, Xiao Yang, Hang Su, Jun Zhu

The use of Transformer is rooted in the need of extracting local discriminative features adaptively for different labels, which is a strongly desired property due to the existence of multiple objects in one image.

Multi-Label Classification

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks

no code implementations5 Jul 2021 Xiao Yang, Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu

Transfer-based adversarial attacks can effectively evaluate model robustness in the black-box setting.

Accumulative Poisoning Attacks on Real-time Data

1 code implementation18 Jun 2021 Tianyu Pang, Xiao Yang, Yinpeng Dong, Hang Su, Jun Zhu

Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy.

Federated Learning

Exploring Memorization in Adversarial Training

no code implementations3 Jun 2021 Yinpeng Dong, Ke Xu, Xiao Yang, Tianyu Pang, Zhijie Deng, Hang Su, Jun Zhu

In this paper, we investigate the memorization effect in adversarial training (AT) for promoting a deeper understanding of capacity, convergence, generalization, and especially robust overfitting of adversarially trained classifiers.

Unsupervised Part Segmentation through Disentangling Appearance and Shape

no code implementations CVPR 2021 Shilong Liu, Lei Zhang, Xiao Yang, Hang Su, Jun Zhu

We study the problem of unsupervised discovery and segmentation of object parts, which, as an intermediate local representation, are capable of finding intrinsic object structure and providing more explainable recognition results.

Semantic Segmentation

Adversarial Open Domain Adaption for Sketch-to-Photo Synthesis

2 code implementations12 Apr 2021 Xiaoyu Xiang, Ding Liu, Xiao Yang, Yiheng Zhu, Xiaohui Shen, Jan P. Allebach

In this paper, we explore the open-domain sketch-to-photo translation, which aims to synthesize a realistic photo from a freehand sketch with its class label, even if the sketches of that class are missing in the training data.

Domain Adaptation Image-to-Image Translation +1

PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information

no code implementations31 Mar 2021 Linchao He, Mengting Luo, Dejun Zhang, Xiao Yang, Hu Chen, Yi Zhang

In this paper, we introduce the homotopy equivalence relation (HER) to make the neural networks learn the data distribution from a high-dimension manifold.

Contrastive Learning Point Cloud Classification

LiBRe: A Practical Bayesian Approach to Adversarial Detection

1 code implementation CVPR 2021 Zhijie Deng, Xiao Yang, Shizhen Xu, Hang Su, Jun Zhu

Despite their appealing flexibility, deep neural networks (DNNs) are vulnerable against adversarial examples.

Adversarial Defense

Black-box Detection of Backdoor Attacks with Limited Information and Data

no code implementations24 Mar 2021 Yinpeng Dong, Xiao Yang, Zhijie Deng, Tianyu Pang, Zihao Xiao, Hang Su, Jun Zhu

Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments.

Joint Network Topology Inference via Structured Fusion Regularization

no code implementations5 Mar 2021 Yanli Yuan, De Wen Soh, Xiao Yang, Kun Guo, Tony Q. S. Quek

Theoretically, we provide a theoretical analysis of the proposed graph estimator, which establishes a non-asymptotic bound of the estimation error under the high-dimensional setting and reflects the effect of several key factors on the convergence rate of our algorithm.

Incentive Mechanism Design for ROI-constrained Auto-bidding

no code implementations4 Dec 2020 Bin Li, Xiao Yang, Daren Sun, Zhi Ji, Zhen Jiang, Cong Han, Dong Hao

Auto-bidding plays an important role in online advertising and has become a crucial tool for advertisers and advertising platforms to meet their performance objectives and optimize the efficiency of ad delivery.

Computer Science and Game Theory

BayesAdapter: Being Bayesian, Inexpensively and Reliably, via Bayesian Fine-tuning

1 code implementation5 Oct 2020 Zhijie Deng, Hao Zhang, Xiao Yang, Yinpeng Dong, Jun Zhu

Despite their theoretical appealingness, Bayesian neural networks (BNNs) are left behind in real-world adoption, due to persistent concerns on their scalability, accessibility, and reliability.

Variational Inference

Bag of Tricks for Adversarial Training

2 code implementations ICLR 2021 Tianyu Pang, Xiao Yang, Yinpeng Dong, Hang Su, Jun Zhu

Adversarial training (AT) is one of the most effective strategies for promoting model robustness.

Qlib: An AI-oriented Quantitative Investment Platform

1 code implementation22 Sep 2020 Xiao Yang, Weiqing Liu, Dong Zhou, Jiang Bian, Tie-Yan Liu

Quantitative investment aims to maximize the return and minimize the risk in a sequential trading period over a set of financial instruments.

Platform Portfolio Optimization +1

Delving into the Adversarial Robustness on Face Recognition

2 code implementations8 Jul 2020 Xiao Yang, Dingcheng Yang, Yinpeng Dong, Wenjian Yu, Hang Su, Jun Zhu

However, the lack of robustness in deep CNNs to adversarial examples has raised security concerns to enormous face recognition applications.

Face Recognition

Noise-robust Named Entity Understanding for Virtual Assistants

no code implementations29 May 2020 Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Lin Li, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason Williams

Named Entity Understanding (NEU) plays an essential role in interactions between users and voice assistants, since successfully identifying entities and correctly linking them to their standard forms is crucial to understanding the user's intent.

Entity Linking Named Entity Recognition +2

Towards Privacy Protection by Generating Adversarial Identity Masks

no code implementations15 Mar 2020 Xiao Yang, Yinpeng Dong, Tianyu Pang, Jun Zhu, Hang Su

As billions of personal data such as photos are shared through social media and network, the privacy and security of data have drawn an increasing attention.

Face Recognition

Boosting Adversarial Training with Hypersphere Embedding

1 code implementation NeurIPS 2020 Tianyu Pang, Xiao Yang, Yinpeng Dong, Kun Xu, Jun Zhu, Hang Su

Adversarial training (AT) is one of the most effective defenses against adversarial attacks for deep learning models.

Representation Learning

Benchmarking Adversarial Robustness

no code implementations26 Dec 2019 Yinpeng Dong, Qi-An Fu, Xiao Yang, Tianyu Pang, Hang Su, Zihao Xiao, Jun Zhu

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning.

Adversarial Attack Image Classification

Design and Interpretation of Universal Adversarial Patches in Face Detection

no code implementations ECCV 2020 Xiao Yang, Fangyun Wei, Hongyang Zhang, Jun Zhu

We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors.

Face Detection

AiAds: Automated and Intelligent Advertising System for Sponsored Search

no code implementations28 Jul 2019 Xiao Yang, Daren Sun, Ruiwei Zhu, Tao Deng, Zhi Guo, Jiao Ding, Shouke Qin, Zongyao Ding, Yanfeng Zhu

Sponsored search has more than 20 years of history, and it has been proven to be a successful business model for online advertising.

Global Optimization Platform

TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade

no code implementations9 Sep 2018 Dafang He, Xiao Yang, Daniel Kifer, C. Lee Giles

We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be effectively used to extract instance-level text contour from natural images.

Scene Text Scene Text Detection

Distractor Generation for Multiple Choice Questions Using Learning to Rank

1 code implementation WS 2018 Chen Liang, Xiao Yang, Neisarg Dave, Drew Wham, Bart Pursel, C. Lee Giles

We investigate how machine learning models, specifically ranking models, can be used to select useful distractors for multiple choice questions.

Distractor Generation Ensemble Learning +1

Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching

no code implementations22 Apr 2018 Xiao Yang, Miaosen Wang, Wei Wang, Madian Khabsa, Ahmed Awadallah, Daniel Kifer, C. Lee Giles

We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue.

Answer Selection General Classification

Fast Predictive Simple Geodesic Regression

no code implementations15 Nov 2017 Zhipeng Ding, Greg Fleishman, Xiao Yang, Paul Thompson, Roland Kwitt, Marc Niethammer

Deformable image registration and regression are important tasks in medical image analysis.

Image Registration

Learning non-parametric Markov networks with mutual information

1 code implementation8 Aug 2017 Janne Leppä-aho, Santeri Räisänen, Xiao Yang, Teemu Roos

We propose a method for learning Markov network structures for continuous data without invoking any assumptions about the distribution of the variables.

Efficient Registration of Pathological Images: A Joint PCA/Image-Reconstruction Approach

no code implementations31 Mar 2017 Xu Han, Xiao Yang, Stephen Aylward, Roland Kwitt, Marc Niethammer

Registration involving one or more images containing pathologies is challenging, as standard image similarity measures and spatial transforms cannot account for common changes due to pathologies.

Image Reconstruction

Fast Predictive Multimodal Image Registration

no code implementations31 Mar 2017 Xiao Yang, Roland Kwitt, Martin Styner, Marc Niethammer

We introduce a deep encoder-decoder architecture for image deformation prediction from multimodal images.

Image Registration

Fast Predictive Image Registration

no code implementations8 Jul 2016 Xiao Yang, Roland Kwitt, Marc Niethammer

We present a method to predict image deformations based on patch-wise image appearance.

Image Registration

Using Word Embeddings in Twitter Election Classification

no code implementations22 Jun 2016 Xiao Yang, Craig Macdonald, Iadh Ounis

In this paper, using a Twitter election classification task that aims to detect election-related tweets, we investigate the impact of the background dataset used to train the embedding models, the context window size and the dimensionality of word embeddings on the classification performance.

General Classification Sentiment Analysis +1

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