Search Results for author: Tao Li

Found 70 papers, 22 papers with code

Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios

no code implementations23 Dec 2021 Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang, Lei Xie, Guoqiao Yu, Guanglu Wan

Moreover, the explicit prosody features used in the prosody predicting module can increase the diversity of synthetic speech by adjusting the value of prosody features.

Speech Synthesis Style Transfer +1

M2DGR: A Multi-sensor and Multi-scenario SLAM Dataset for Ground Robots

1 code implementation19 Dec 2021 Jie Yin, Ang Li, Tao Li, Wenxian Yu, Danping Zou

We introduce M2DGR: a novel large-scale dataset collected by a ground robot with a full sensor-suite including six fish-eye and one sky-pointing RGB cameras, an infrared camera, an event camera, a Visual-Inertial Sensor (VI-sensor), an inertial measurement unit (IMU), a LiDAR, a consumer-grade Global Navigation Satellite System (GNSS) receiver and a GNSS-IMU navigation system with real-time kinematic (RTK) signals.

One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation

no code implementations24 Nov 2021 Zhichao Wang, Qicong Xie, Tao Li, Hongqiang Du, Lei Xie, Pengcheng Zhu, Mengxiao Bi

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness.

Speech Quality Style Transfer +1

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.

Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion

no code implementations16 Jun 2021 Zhichao Wang, Xinyong Zhou, Fengyu Yang, Tao Li, Hongqiang Du, Lei Xie, Wendong Gan, Haitao Chen, Hai Li

Specifically, prosodic features are used to explicit model prosody, while VAE and reference encoder are used to implicitly model prosody, which take Mel spectrum and bottleneck feature as input respectively.

Speech Quality Style Transfer +1

The Confluence of Networks, Games and Learning

no code implementations17 May 2021 Tao Li, Guanze Peng, Quanyan Zhu, Tamer Basar

In addition to existing research works on game-theoretic learning over networks, we highlight several new angles and research endeavors on learning in games that are related to recent developments in artificial intelligence.

Decision Making

DeepBlur: A Simple and Effective Method for Natural Image Obfuscation

no code implementations31 Mar 2021 Tao Li, Min Soo Choi

There is a growing privacy concern due to the popularity of social media and surveillance systems, along with advances in face recognition software.

Face Recognition

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

Differentially Private Imaging via Latent Space Manipulation

no code implementations8 Mar 2021 Tao Li, Chris Clifton

There is growing concern about image privacy due to the popularity of social media and photo devices, along with increasing use of face recognition systems.

De-identification Face Recognition

Strongly Connected Topology Model and Confirmation-based Propagation Method for Cross-chain Interaction

no code implementations18 Feb 2021 Hong Su, Bing Guo, Yan Shen, Tao Li

Meanwhile, different from legacy networks, the propagation method is required to keep the data validity.

Distributed, Parallel, and Cluster Computing

Signal identification with Kalman Filter towards background-free neutrinoless double beta decay searches in gaseous detectors

no code implementations16 Feb 2021 Tao Li, Shaobo Wang, Yu Chen, Ke Han, Heng Lin, Kaixiang Ni, Wei Wang, Yiliu Xu, Anni Zou

Particle tracks and differential energy loss measured in high pressure gaseous detectors can be exploited for event identification in neutrinoless double beta decay~($0\nu \beta \beta$) searches.

Instrumentation and Detectors High Energy Physics - Experiment

A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection

no code implementations16 Feb 2021 Ning li, Tao Li, Chunyu Hu, Kai Wang, Hong Kang

In ophthalmology, early fundus screening is an economic and effective way to prevent blindness caused by ophthalmic diseases.

Applications of Deep Learning in Fundus Images: A Review

1 code implementation25 Jan 2021 Tao Li, Wang Bo, Chunyu Hu, Hong Kang, Hanruo Liu, Kai Wang, Huazhu Fu

The use of fundus images for the early screening of eye diseases is of great clinical importance.

Image Generation Lesion Segmentation

Blackwell Online Learning for Markov Decision Processes

no code implementations28 Dec 2020 Tao Li, Guanze Peng, Quanyan Zhu

This work provides a novel interpretation of Markov Decision Processes (MDP) from the online optimization viewpoint.

Learning Theory Q-Learning

Slow Control System for PandaX-III experiment

no code implementations24 Dec 2020 Xiyu Yan, Xun Chen, Yu Chen, Bo Dai, Heng Lin, Tao Li, Ke Han, Kaixiang Ni, Fusang Wang, Shaobo Wang, Qibin Zheng, Xinning Zeng

The PandaX-III experiment uses high pressure gaseous time projection chamber to search for the neutrinoless double beta decay of $^{136}$Xe.

Anomaly Detection High Energy Physics - Experiment Instrumentation and Detectors

Locally-Aware Constrained Games on Networks

no code implementations19 Nov 2020 Guanze Peng, Tao Li, Shutian Liu, Juntao Chen, Quanyan Zhu

We use \textit{awareness levels} to capture the scope of the network constraints that players are aware of.

An Empirical-cum-Statistical Approach to Power-Performance Characterization of Concurrent GPU Kernels

no code implementations4 Nov 2020 Nilanjan Goswami, Amer Qouneh, Chao Li, Tao Li

Growing deployment of power and energy efficient throughput accelerators (GPU) in data centers demands enhancement of power-performance co-optimization capabilities of GPUs.

Distributed, Parallel, and Cluster Computing Hardware Architecture Graphics

Learning Causal Semantic Representation for Out-of-Distribution Prediction

1 code implementation NeurIPS 2021 Chang Liu, Xinwei Sun, Jindong Wang, Haoyue Tang, Tao Li, Tao Qin, Wei Chen, Tie-Yan Liu

Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.

Domain Adaptation

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

UnQovering Stereotyping Biases via Underspecified Questions

1 code implementation Findings of the Association for Computational Linguistics 2020 Tao Li, Tushar Khot, Daniel Khashabi, Ashish Sabharwal, Vivek Srikumar

Our broad study reveals that (1) all these models, with and without fine-tuning, have notable stereotyping biases in these classes; (2) larger models often have higher bias; and (3) the effect of fine-tuning on bias varies strongly with the dataset and the model size.

Question Answering

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.

On Data Augmentation for Extreme Multi-label Classification

no code implementations22 Sep 2020 Danqing Zhang, Tao Li, Haiyang Zhang, Bing Yin

Our contributions are two-factored: (1) we introduce a new state-of-the-art classifier that uses label attention with RoBERTa and combine it with our augmentation framework for further improvement; (2) we present a broad study on how effective are different augmentation methods in the XMC task.

Data Augmentation Extreme Multi-Label Classification +2

Attention-SLAM: A Visual Monocular SLAM Learning from Human Gaze

1 code implementation15 Sep 2020 Jinquan Li, Ling Pei, Danping Zou, Songpengcheng Xia, Qi Wu, Tao Li, Zhen Sun, Wenxian Yu

This paper proposes a novel simultaneous localization and mapping (SLAM) approach, namely Attention-SLAM, which simulates human navigation mode by combining a visual saliency model (SalNavNet) with traditional monocular visual SLAM.

Simultaneous Localization and Mapping

OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings

1 code implementation EMNLP 2021 Sunipa Dev, Tao Li, Jeff M. Phillips, Vivek Srikumar

Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks.

Rectification Word Embeddings

Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning

no code implementations16 Jun 2020 Jie An, Tao Li, Hao-Zhi Huang, Li Shen, Xuan Wang, Yongyi Tang, Jinwen Ma, Wei Liu, Jiebo Luo

Extracting effective deep features to represent content and style information is the key to universal style transfer.

Style Transfer

VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization

1 code implementation18 May 2020 Cheng Gong, Yao Chen, Ye Lu, Tao Li, Cong Hao, Deming Chen

Quantization has been proven to be an effective method for reducing the computing and/or storage cost of DNNs.

Model Compression Object Detection +1

AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack

no code implementations6 May 2020 Ao Liu, Beibei Li, Tao Li, Pan Zhou, Rui Wang

In this paper, we first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks.

Adversarial Attack General Classification +3

Structured Tuning for Semantic Role Labeling

1 code implementation ACL 2020 Tao Li, Parth Anand Jawale, Martha Palmer, Vivek Srikumar

We start with a strong baseline (RoBERTa) to validate the impact of our approach, and show that our framework outperforms the baseline by learning to comply with declarative constraints.

Semantic Role Labeling

Cooperative Extended State Observer Based Control of Vehicle Platoons With Arbitrarily Small Time Headway

no code implementations21 Apr 2020 Anquan Liu, Tao Li, Yu Gu, Haohui Dai

By using the stability theory of perturbed linear systems, we show that the control parameters can be properly designed to ensure the closed-loop and L2 string stabilities for any given positive time headway.

Self-Learning with Rectification Strategy for Human Parsing

no code implementations CVPR 2020 Tao Li, Zhiyuan Liang, Sanyuan Zhao, Jiahao Gong, Jianbing Shen

For the global error, we first transform category-wise features into a high-level graph model with coarse-grained structural information, and then decouple the high-level graph to reconstruct the category features.

Human Parsing Rectification

SFE-GACN: A Novel Unknown Attack Detection Method Using Intra Categories Generation in Embedding Space

no code implementations12 Apr 2020 Ao Liu, Yunpeng Wang, Tao Li

In this paper, we propose a novel unknown attack detection method based on Intra Categories Generation in Embedding Space, namely SFE-GACN, which might be the solution of few-shot problem.

Data Augmentation Intrusion Detection

A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors

no code implementations4 Mar 2020 Fanyi Xiao, Ling Pei, Lei Chu, Danping Zou, Wenxian Yu, Yifan Zhu, Tao Li

The experimental results show that the proposed method can surprisingly converge in a few iterations and achieve an accuracy of 91. 15% on a real IMU dataset, demonstrating the efficiency and effectiveness of the proposed method.

Activity Recognition Transfer Learning

Phylogenetic study of 2019-nCoV by using alignment-free method

no code implementations3 Mar 2020 Yang Gao, Tao Li, Liaofu Luo

The origin and early spread of 2019-nCoV is studied by phylogenetic analysis using IC-PIC alignment-free method based on DNA/RNA sequence information correlation (IC) and partial information correlation (PIC).

Mutually unbiased measurement based entanglement witnesses

no code implementations4 Dec 2019 Tao Li, Le-Min Lai, Shao-Ming Fei, Zhi-Xi Wang

We study entanglement witness and present a construction of entanglement witnesses in terms of the mutually unbiased measurements (MUMs).

Quantum Physics

Component Attention Guided Face Super-Resolution Network: CAGFace

1 code implementation19 Oct 2019 Ratheesh Kalarot, Tao Li, Fatih Porikli

To make the best use of the underlying structure of faces, the collective information through face datasets and the intermediate estimates during the upsampling process, here we introduce a fully convolutional multi-stage neural network for 4$\times$ super-resolution for face images.


A Logic-Driven Framework for Consistency of Neural Models

1 code implementation IJCNLP 2019 Tao Li, Vivek Gupta, Maitrey Mehta, Vivek Srikumar

While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples.

Natural Language Inference

On Measuring and Mitigating Biased Inferences of Word Embeddings

1 code implementation25 Aug 2019 Sunipa Dev, Tao Li, Jeff Phillips, Vivek Srikumar

Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them.

Natural Language Inference Word Embeddings

On Convergence Rate of Adaptive Multiscale Value Function Approximation For Reinforcement Learning

no code implementations22 Aug 2019 Tao Li, Quanyan Zhu

In this paper, we propose a generic framework for devising an adaptive approximation scheme for value function approximation in reinforcement learning, which introduces multiscale approximation.

Decentralized Cooperative Online Estimation With Random Observation Matrices, Communication Graphs and Time Delays

no code implementations22 Aug 2019 Jiexiang Wang, Tao Li, Xiwei Zhang

Firstly, for the delay-free case, we show that the algorithm gains can be designed properly such that all nodes' estimates converge to the true parameter in mean square and almost surely if the observation matrices and communication graphs satisfy the stochastic spatiotemporal persistence of excitation condition.

A Pvalue-guided Anomaly Detection Approach Combining Multiple Heterogeneous Log Parser Algorithms on IIoT Systems

no code implementations5 Jul 2019 Xueshuo Xie, Zhi Wang, Xuhang Xiao, Lei Yang, Shenwei Huang, Tao Li

In this paper, we use blockchain to prevent logs from being tampered with and propose a pvalue-guided anomaly detection approach.

Cryptography and Security

Augmenting Neural Networks with First-order Logic

1 code implementation ACL 2019 Tao Li, Vivek Srikumar

Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset.

Chunking Natural Language Inference +1

Beauty Learning and Counterfactual Inference

no code implementations24 Apr 2019 Tao Li

This work showcases a new approach for causal discovery by leveraging user experiments and recent advances in photo-realistic image editing, demonstrating a potential of identifying causal factors and understanding complex systems counterfactually.

Causal Discovery Counterfactual Inference

T-SVD Based Non-convex Tensor Completion and Robust Principal Component Analysis

no code implementations23 Apr 2019 Tao Li, Jinwen Ma

Tensor completion and robust principal component analysis have been widely used in machine learning while the key problem relies on the minimization of a tensor rank that is very challenging.

Denoising Image Inpainting

BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving

1 code implementation15 Mar 2019 Jianru Xue, Jianwu Fang, Tao Li, Bohua Zhang, Pu Zhang, Zhen Ye, Jian Dou

Instead, BLVD aims to provide a platform for the tasks of dynamic 4D (3D+temporal) tracking, 5D (4D+interactive) interactive event recognition and intention prediction.

Autonomous Driving Instance Segmentation +2

Understanding Beauty via Deep Facial Features

no code implementations30 Jan 2019 Xudong Liu, Tao Li, Hao Peng, Iris Chuoying Ouyang, Taehwan Kim, Ruizhe Wang

The concept of beauty has been debated by philosophers and psychologists for centuries, but most definitions are subjective and metaphysical, and deficit in accuracy, generality, and scalability.

Student's t-Generative Adversarial Networks

no code implementations6 Nov 2018 Jinxuan Sun, Guoqiang Zhong, Yang Chen, Yongbin Liu, Tao Li, Zhongwen Guo

We propose a new method referring to conditional GAN, which equipments the latent noise with mixture of Student's t-distribution with attention mechanism in addition to class information.

Image Generation

Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension

no code implementations EMNLP 2018 Shusen Liu, Tao Li, Zhimin Li, Vivek Srikumar, Valerio Pascucci, Peer-Timo Bremer

Neural networks models have gained unprecedented popularity in natural language processing due to their state-of-the-art performance and the flexible end-to-end training scheme.

Decision Making Natural Language Inference +1

Structure Learning of Deep Networks via DNA Computing Algorithm

no code implementations25 Oct 2018 Guoqiang Zhong, Tao Li, Wenxue Liu, Yang Chen

The indicates that: 1) Using DNA computing algorithm to learn deep architectures is feasible; 2) Local minima should not be a problem of deep networks; 3) We can use early stop to kill the models with the bad performance just after several runs of training.

GPU based Parallel Optimization for Real Time Panoramic Video Stitching

no code implementations4 Oct 2018 Chengyao Du, Jingling Yuan, Jiansheng Dong, Lin Li, Mincheng Chen, Tao Li

In order to solve these problems, we propose a real-time panoramic video stitching framework. The framework we propose mainly consists of three algorithms, LORB image feature extraction algorithm, feature point matching algorithm based on LSH and GPU parallel video stitching algorithm based on CUDA. The experiment results show that the algorithm mentioned can improve the performance in the stages of feature extraction of images stitching and matching, the running speed of which is 11 times than that of the traditional ORB algorithm and 639 times than that of the traditional SIFT algorithm.

Image Stitching

Semi-supervised Text Regression with Conditional Generative Adversarial Networks

no code implementations2 Oct 2018 Tao Li, Xudong Liu, Shih-An Su

Enormous online textual information provides intriguing opportunities for understandings of social and economic semantics.

HashTran-DNN: A Framework for Enhancing Robustness of Deep Neural Networks against Adversarial Malware Samples

no code implementations18 Sep 2018 Deqiang Li, Ramesh Baral, Tao Li, Han Wang, Qianmu Li, Shouhuai Xu

Adversarial machine learning in the context of image processing and related applications has received a large amount of attention.

Denoising Malware Detection

YouTube AV 50K: An Annotated Corpus for Comments in Autonomous Vehicles

1 code implementation30 Jul 2018 Tao Li, Lei Lin, Minsoo Choi, Kaiming Fu, Siyuan Gong, Jian Wang

With one billion monthly viewers, and millions of users discussing and sharing opinions, comments below YouTube videos are rich sources of data for opinion mining and sentiment analysis.

Opinion Mining Self-Driving Cars +1

Aspect Based Sentiment Analysis with Gated Convolutional Networks

1 code implementation ACL 2018 Wei Xue, Tao Li

Aspect based sentiment analysis (ABSA) can provide more detailed information than general sentiment analysis, because it aims to predict the sentiment polarities of the given aspects or entities in text.

Aspect-Based Sentiment Analysis

Collaborative Filtering with Topic and Social Latent Factors Incorporating Implicit Feedback

no code implementations26 Mar 2018 Guang-Neng Hu, Xin-yu Dai, Feng-Yu Qiu, Rui Xia, Tao Li, Shu-Jian Huang, Jia-Jun Chen

First, we propose a novel model {\em \mbox{MR3}} to jointly model three sources of information (i. e., ratings, item reviews, and social relations) effectively for rating prediction by aligning the latent factors and hidden topics.

Collaborative Filtering Recommendation Systems

BTS-DSN: Deeply Supervised Neural Network with Short Connections for Retinal Vessel Segmentation

1 code implementation11 Mar 2018 Song Guo, Kai Wang, Hong Kang, Yujun Zhang, Yingqi Gao, Tao Li

Results: The proposed BTS-DSN has been verified on DRIVE, STARE and CHASE_DB1 datasets, and showed competitive performance over other state-of-the-art methods.

Retinal Vessel Segmentation

A Class-Incremental Learning Method Based on One Class Support Vector Machine

no code implementations1 Mar 2018 Chengfei Yao, Jie Zou, Yanan Luo, Tao Li, Gang Bai

Then the support vectors of the old classes and the support vectors of the new class are reused to train 1VS1 classifiers for the confuse part.

class-incremental learning Incremental Learning

HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Image

2 code implementations28 Feb 2018 Yanan Luo, Jie Zou, Chengfei Yao, Tao Li, Gang Bai

In this paper, we propose a novel convolutional neural network framework for the characteristics of hyperspectral image data, called HSI-CNN.

General Classification Hyperspectral Image Classification

MTNA: A Neural Multi-task Model for Aspect Category Classification and Aspect Term Extraction On Restaurant Reviews

no code implementations IJCNLP 2017 Wei Xue, Wubai Zhou, Tao Li, Qing Wang

Online reviews are valuable resources not only for consumers to make decisions before purchase, but also for providers to get feedbacks for their services or commodities.

Extract Aspect General Classification +4

Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms

no code implementations10 Aug 2017 Qing Wang, Chunqiu Zeng, Wubai Zhou, Tao Li, Larisa Shwartz, Genady Ya. Grabarnik

To address these issues, collaborative filtering (CF), one of the recommendation techniques relying on the interaction data only, as well as the online multi-armed bandit mechanisms, capable of achieving the balance between exploitation and exploration, are adopted in the online interactive recommendation settings, by assuming independent items (i. e., arms).

Collaborative Filtering Recommendation Systems

Lesion detection and Grading of Diabetic Retinopathy via Two-stages Deep Convolutional Neural Networks

no code implementations2 May 2017 Yehui Yang, Tao Li, Wensi Li, Haishan Wu, Wei Fan, Wensheng Zhang

We propose an automatic diabetic retinopathy (DR) analysis algorithm based on two-stages deep convolutional neural networks (DCNN).

Z$_{2}$ spin liquid phase on the kagome lattice: a new saddle point

1 code implementation9 Jan 2016 Tao Li

The Z$_{2}$ state is found to be slightly more stable than the extensively studied U(1) gapless Dirac spin liquid state in both the $J_{2}\neq0$ and the $J_{2}=0$ case and to possess a small spinon gap for $J_{2}<0. 2$.

Strongly Correlated Electrons

Skopus: Mining top-k sequential patterns under leverage

1 code implementation26 Jun 2015 Francois Petitjean, Tao Li, Nikolaj Tatti, Geoffrey I. Webb

It combines (1) a novel definition of the expected support for a sequential pattern - a concept on which most interestingness measures directly rely - with (2) SkOPUS: a new branch-and-bound algorithm for the exact discovery of top-k sequential patterns under a given measure of interest.

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