Search Results for author: Lei Xu

Found 39 papers, 9 papers with code

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm

1 code implementation11 Apr 2022 Lei Xu, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Zhiyuan Liu

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting.

Sufficient Reasons for A Zero-Day Intrusion Detection Artificial Immune System

no code implementations5 Apr 2022 Qianru Zhou, Rongzhen Li, Lei Xu, Arumugam Nallanathan, Jian Yanga, Anmin Fu

With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more.

Intrusion Detection

IA-FaceS: A Bidirectional Method for Semantic Face Editing

no code implementations24 Mar 2022 Wenjing Huang, Shikui Tu, Lei Xu

To strike a balance between the reconstruction capacity and the control flexibility, the encoder is designed as a multi-head structure to yield embeddings for reconstruction and control, respectively: a high-dimensional tensor with spatial properties for consistent reconstruction and four low-dimensional facial component embeddings for semantic face editing.

Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking

no code implementations20 Mar 2022 Lei Xu, Tianyu Ren, Georgia Chalvatzaki, Jan Peters

Task and Motion Planning (TAMP) provides a hierarchical framework to handle the sequential nature of manipulation tasks by interleaving a symbolic task planner that generates a possible action sequence, with a motion planner that checks the kinematic feasibility in the geometric world, generating robot trajectories if several constraints are satisfied, e. g., a collision-free trajectory from one state to another.

Motion Planning

The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining

no code implementations14 Mar 2022 Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, Bo Li

Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process.

Federated Learning

HDL: Hybrid Deep Learning for the Synthesis of Myocardial Velocity Maps in Digital Twins for Cardiac Analysis

no code implementations9 Mar 2022 Xiaodan Xing, Javier Del Ser, Yinzhe Wu, Yang Li, Jun Xia, Lei Xu, David Firmin, Peter Gatehouse, Guang Yang

A core part of digital healthcare twins is model-based data synthesis, which permits the generation of realistic medical signals without requiring to cope with the modelling complexity of anatomical and biochemical phenomena producing them in reality.

Decision Making Left Ventricle Segmentation

D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention

no code implementations2 Mar 2022 Junyu Lin, Xiaofeng Mao, Yuefeng Chen, Lei Xu, Yuan He, Hui Xue

DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing.

D$^2$ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention

no code implementations29 Sep 2021 Junyu Lin, Xiaofeng Mao, Yuefeng Chen, Lei Xu, Yuan He, Hui Xue'

DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing.

Deep Rival Penalized Competitive Learning for Low-resolution Face Recognition

no code implementations3 Aug 2021 Peiying Li, Shikui Tu, Lei Xu

Current face recognition tasks are usually carried out on high-quality face images, but in reality, most face images are captured under unconstrained or poor conditions, e. g., by video surveillance.

Face Recognition

DeceFL: A Principled Decentralized Federated Learning Framework

1 code implementation15 Jul 2021 Ye Yuan, Jun Liu, Dou Jin, Zuogong Yue, Ruijuan Chen, Maolin Wang, Chuan Sun, Lei Xu, Feng Hua, Xin He, Xinlei Yi, Tao Yang, Hai-Tao Zhang, Shaochun Sui, Han Ding

Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.

Federated Learning

A Photonic-Circuits-Inspired Compact Network: Toward Real-Time Wireless Signal Classification at the Edge

1 code implementation25 Jun 2021 Hsuan-Tung Peng, Joshua Lederman, Lei Xu, Thomas Ferreira de Lima, Chaoran Huang, Bhavin Shastri, David Rosenbluth, Paul Prucnal

In addition, compact and integratable hardware platforms which can implement ML models at the chip scale will find much broader application to wireless communication networks.

Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining

no code implementations25 Apr 2021 Xiang Chen, Yufeng Huang, Lei Xu

Rain streaks bring serious blurring and visual quality degradation, which often vary in size, direction and density.

Single Image Deraining

Attacking Text Classifiers via Sentence Rewriting Sampler

1 code implementation17 Apr 2021 Lei Xu, Kalyan Veeramachaneni

Most adversarial attack methods on text classification can change the classifier's prediction by synonym substitution.

Adversarial Attack General Classification +4

EDSC: An Event-Driven Smart Contract Platform

no code implementations14 Jan 2021 Mudabbir Kaleem, Keshav Kasichainula, Rabimba Karanjai, Lei Xu, Zhimin Gao, Lin Chen, Weidong Shi

This paper presents EDSC, a novel smart contract platform design based on the event-driven execution model as opposed to the traditionally employed transaction-driven execution model.

Distributed, Parallel, and Cluster Computing

Planar narrow-band-pass filter based on Si resonant metasurface

no code implementations19 Dec 2020 Ze Zheng, Andrei Komar, Khosro Zangeneh Kamali, John Noble, Lachlan Whichello, Andrey E. Miroshnichenko, Mohsen Rahmani, Dragomir N. Neshev, Lei Xu

Optically resonant dielectric metasurfaces offer unique capability to fully control the wavefront, polarisation, intensity or spectral content of light based on the excitation and interference of different electric and magnetic Mie multipolar resonances.


Rewriting Meaningful Sentences via Conditional BERT Sampling and an application on fooling text classifiers

no code implementations22 Oct 2020 Lei Xu, Ivan Ramirez, Kalyan Veeramachaneni

Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters.

Adversarial Attack Semantic Similarity +1

AutoML to Date and Beyond: Challenges and Opportunities

no code implementations21 Oct 2020 Shubhra Kanti Karmaker Santu, Md. Mahadi Hassan, Micah J. Smith, Lei Xu, ChengXiang Zhai, Kalyan Veeramachaneni

AutoML tools aim to make machine learning accessible for non-machine learning experts (domain experts), to improve the efficiency of machine learning, and to accelerate machine learning research.


Solve Traveling Salesman Problem by Monte Carlo Tree Search and Deep Neural Network

no code implementations14 May 2020 Zhihao Xing, Shikui Tu, Lei Xu

We present a self-learning approach that combines deep reinforcement learning and Monte Carlo tree search to solve the traveling salesman problem.

reinforcement-learning Self-Learning +1

Saliency-based Weighted Multi-label Linear Discriminant Analysis

no code implementations8 Apr 2020 Lei Xu, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

The proposed method is based on a probabilistic model for defining the weights of individual samples in a weighted multi-label LDA approach.

Classification General Classification +1

Simultaneous Left Atrium Anatomy and Scar Segmentations via Deep Learning in Multiview Information with Attention

no code implementations2 Feb 2020 Guang Yang, Jun Chen, Zhifan Gao, Shuo Li, Hao Ni, Elsa Angelini, Tom Wong, Raad Mohiaddin, Eva Nyktari, Ricardo Wage, Lei Xu, Yanping Zhang, Xiuquan Du, Heye Zhang, David Firmin, Jennifer Keegan

Using our MVTT recursive attention model, both the LA anatomy and scar can be segmented accurately (mean Dice score of 93% for the LA anatomy and 87% for the scar segmentations) and efficiently (~0. 27 seconds to simultaneously segment the LA anatomy and scars directly from the 3D LGE CMR dataset with 60-68 2D slices).

Defense against Adversarial Examples by Encoder-Assisted Search in the Latent Coding Space

no code implementations25 Sep 2019 Wenjing Huang, Shikui Tu, Lei Xu

In the inference time, when given an input, we will start a search process in the latent space which aims to find the closest reconstruction to the given image on the distribution of normal data.

Robust Invisible Video Watermarking with Attention

1 code implementation3 Sep 2019 Kevin Alex Zhang, Lei Xu, Alfredo Cuesta-Infante, Kalyan Veeramachaneni

The goal of video watermarking is to embed a message within a video file in a way such that it minimally impacts the viewing experience but can be recovered even if the video is redistributed and modified, allowing media producers to assert ownership over their content.

Multi-owner Secure Encrypted Search Using Searching Adversarial Networks

no code implementations7 Aug 2019 Kai Chen, Zhongrui Lin, Jian Wan, Lei Xu, Chungen Xu

To address this, this paper proposes secure and efficient multi-keyword ranked search over encrypted cloud data for multi-owner model based on searching adversarial networks.

Distributed Computing

Revisit Lmser and its further development based on convolutional layers

no code implementations12 Apr 2019 Wenjing Huang, Shikui Tu, Lei Xu

Proposed in 1991, Least Mean Square Error Reconstruction for self-organizing network, shortly Lmser, was a further development of the traditional auto-encoder (AE) by folding the architecture with respect to the central coding layer and thus leading to the features of symmetric weights and neurons, as well as jointly supervised and unsupervised learning.

A* Tree Search for Portfolio Management

no code implementations7 Jan 2019 Xiaojie Gao, Shikui Tu, Lei Xu

By uniting the advantages in A* search algorithm with Monte Carlo tree search, we come up with a new algorithm named A* tree search in which best information is returned to guide next search.


Synthesizing Tabular Data using Generative Adversarial Networks

7 code implementations27 Nov 2018 Lei Xu, Kalyan Veeramachaneni

Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution.

Computational Decomposition of Style for Controllable and Enhanced Style Transfer

no code implementations21 Nov 2018 Minchao Li, Shikui Tu, Lei Xu

Neural style transfer has been demonstrated to be powerful in creating artistic image with help of Convolutional Neural Networks (CNN).

Style Transfer

Election with Bribed Voter Uncertainty: Hardness and Approximation Algorithm

no code implementations7 Nov 2018 Lin Chen, Lei Xu, Shouhuai Xu, Zhimin Gao, Weidong Shi

In this paper, we introduce a novel variant of the bribery problem, "Election with Bribed Voter Uncertainty" or BVU for short, accommodating the uncertainty that the vote of a bribed voter may or may not be counted.

Lightweight (Reverse) Fuzzy Extractor with Multiple Referenced PUF Responses

no code implementations19 May 2018 Yansong Gao, Yang Su, Lei Xu, Damith C. Ranasinghe

A Physical unclonable functions (PUF), alike a fingerprint, exploits manufacturing randomness to endow each physical item with a unique identifier.

Cryptography and Security

Weighted Linear Discriminant Analysis based on Class Saliency Information

no code implementations19 Feb 2018 Lei Xu, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we propose a new variant of Linear Discriminant Analysis to overcome underlying drawbacks of traditional LDA and other LDA variants targeting problems involving imbalanced classes.

General Classification Image Classification +1

Sketch-pix2seq: a Model to Generate Sketches of Multiple Categories

no code implementations13 Sep 2017 Yajing Chen, Shikui Tu, Yuqi Yi, Lei Xu

Moreover, the combination of CNN encoder and removal of KL-divergence, i. e., the sketch-pix2seq model, had better performance in learning and generating sketches of multiple categories and showed promising results in creativity tasks.

Direct detection of pixel-level myocardial infarction areas via a deep-learning algorithm

no code implementations10 Jun 2017 Chenchu Xu, Lei Xu, Zhifan Gao, Shen zhao, Heye Zhang, Yanping Zhang, Xiuquan Du, Shu Zhao, Dhanjoo Ghista, Shuo Li

Accurate detection of the myocardial infarction (MI) area is crucial for early diagnosis planning and follow-up management.

Time Series

Input Convex Neural Networks

3 code implementations ICML 2017 Brandon Amos, Lei Xu, J. Zico Kolter

We show that many existing neural network architectures can be made input-convex with a minor modification, and develop specialized optimization algorithms tailored to this setting.

Imputation Inference Optimization +2

Topic Sensitive Neural Headline Generation

no code implementations20 Aug 2016 Lei Xu, ZiYun Wang, Ayana, Zhiyuan Liu, Maosong Sun

Neural models have recently been used in text summarization including headline generation.

Headline generation Text Summarization

Structuring Causal Tree Models with Continuous Variables

no code implementations27 Mar 2013 Lei Xu, Judea Pearl

This paper considers the problem of invoking auxiliary, unobservable variables to facilitate the structuring of causal tree models for a given set of continuous variables.

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