Search Results for author: Jun Yang

Found 63 papers, 14 papers with code

Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors

no code implementations17 Sep 2023 Ziwei Liao, Jun Yang, Jingxing Qian, Angela P. Schoellig, Steven L. Waslander

Unlike current state-of-the-art approaches, we explicitly model the uncertainty of the object shapes and poses during our optimization, resulting in a high-quality object-level mapping system.

3D Reconstruction

META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection

no code implementations17 Aug 2023 Jinbo Hu, Yin Cao, Ming Wu, Feiran Yang, Ziying Yu, Wenwu Wang, Mark D. Plumbley, Jun Yang

For learning-based sound event localization and detection (SELD) methods, different acoustic environments in the training and test sets may result in large performance differences in the validation and evaluation stages.

Meta-Learning Sound Event Localization and Detection

Variational Label-Correlation Enhancement for Congestion Prediction

no code implementations1 Aug 2023 Biao Liu, Congyu Qiao, Ning Xu, Xin Geng, Ziran Zhu, Jun Yang

In order to fully exploit the inherent spatial label-correlation between neighboring grids, we propose a novel approach, {\ours}, i. e., VAriational Label-Correlation Enhancement for Congestion Prediction, which considers the local label-correlation in the congestion map, associating the estimated congestion value of each grid with a local label-correlation weight influenced by its surrounding grids.

Variational Inference

Rethinking PRL: A Multiscale Progressively Residual Learning Network for Inverse Halftoning

1 code implementation27 May 2023 Feiyu Li, Jun Yang

Because the halftone images lose much of the original image content, inverse halftoning is a classic ill-problem.

Image Restoration

Learning Diverse Risk Preferences in Population-based Self-play

1 code implementation19 May 2023 Yuhua Jiang, Qihan Liu, Xiaoteng Ma, Chenghao Li, Yiqin Yang, Jun Yang, Bin Liang, Qianchuan Zhao

In this paper, we aim to introduce diversity from the perspective that agents could have diverse risk preferences in the face of uncertainty.

reinforcement-learning Reinforcement Learning (RL)

Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning

1 code implementation10 Apr 2023 Junjie Zhang, Jiafei Lyu, Xiaoteng Ma, Jiangpeng Yan, Jun Yang, Le Wan, Xiu Li

To empirically show the advantages of TATU, we first combine it with two classical model-based offline RL algorithms, MOPO and COMBO.

D4RL Data Augmentation +3

Task-oriented Memory-efficient Pruning-Adapter

1 code implementation26 Mar 2023 Guorun Wang, Jun Yang, Yaoru Sun

Adapters are to freeze the model and give it a new weight matrix on the side, which can significantly reduce the time and memory of training, but the cost is that the evaluation and testing will increase the time and memory consumption.

Pixel Difference Convolutional Network for RGB-D Semantic Segmentation

no code implementations23 Feb 2023 Jun Yang, Lizhi Bai, Yaoru Sun, Chunqi Tian, Maoyu Mao, Guorun Wang

For the Depth branch, we propose a Pixel Difference Convolution (PDC) to consider local and detailed geometric information in Depth data via aggregating both intensity and gradient information.

Semantic Segmentation

Selective Noise Suppression Methods Using Random SVPWM to Shape the Noise Spectrum of PMSMs

1 code implementation16 Feb 2023 Jian Wen, Xiaobin Cheng, Peifeng Ji, Jun Yang, Feng Zhao

Both the pulse position and switching frequency are randomized in the second method.

Dual Control of Exploration and Exploitation for Self-Optimisation Control in Uncertain Environments

no code implementations27 Jan 2023 Zhongguo Li, Wen-Hua Chen, Jun Yang, Yunda Yan

This paper develops a dual control framework for exploration and exploitation (DCEE) to solve a self-optimisation problem in unknown and uncertain environment.

Edge Enhanced Image Style Transfer via Transformers

no code implementations2 Jan 2023 Chiyu Zhang, Jun Yang, Zaiyan Dai, Peng Cao

In recent years, arbitrary image style transfer has attracted more and more attention.

Style Transfer

Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation

no code implementations ICCV 2023 Guangnian Wan, Haitao Du, Xuejing Yuan, Jun Yang, Meiling Chen, Jie Xu

Previous attacks assume the adversary can infer the local learning rate of each client, while we observe that: (1) using the uniformly distributed random local learning rates does not incur much accuracy loss of the global model, and (2) personalizing local learning rates can mitigate the drift issue which is caused by non-IID (identically and independently distributed) data.

Federated Learning

S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention

1 code implementation22 Oct 2022 Chiyu Zhang, Jun Yang, Lei Wang, Zaiyan Dai

This paper presents a new hierarchical vision Transformer for image style transfer, called Strips Window Attention Transformer (S2WAT), which serves as an encoder of encoder-transfer-decoder architecture.

Style Transfer

DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation

no code implementations13 Oct 2022 Lizhi Bai, Jun Yang, Chunqi Tian, Yaoru Sun, Maoyu Mao, Yanjun Xu, Weirong Xu

A two-branch network built with DCA and EDCA, called Differential Convolutional Network (DCANet), is proposed to fuse local and global information of two-modal data.

Semantic Segmentation

SmartFPS: Neural Network based Wireless-inertial fusion positioning system

no code implementations27 Sep 2022 Luchi Hua, Jun Yang

The current fusion positioning systems are mainly based on filtering algorithms, such as Kalman filtering or particle filtering.

Transfer Learning

Tuning Stochastic Gradient Algorithms for Statistical Inference via Large-Sample Asymptotics

no code implementations25 Jul 2022 Jeffrey Negrea, Jun Yang, Haoyue Feng, Daniel M. Roy, Jonathan H. Huggins

The tuning of stochastic gradient algorithms (SGAs) for optimization and sampling is often based on heuristics and trial-and-error rather than generalizable theory.

Stereographic Markov Chain Monte Carlo

no code implementations24 May 2022 Jun Yang, Krzysztof Łatuszyński, Gareth O. Roberts

High dimensional distributions, especially those with heavy tails, are notoriously difficult for off-the-shelf MCMC samplers: the combination of unbounded state spaces, diminishing gradient information, and local moves, results in empirically observed "stickiness" and poor theoretical mixing properties -- lack of geometric ergodicity.

IR-ORAM: Path Access Type Based Memory Intensity Reduction for Path-ORAM

no code implementations IEEE International Symposium on High-Performance Computer Architecture (HPCA) 2022 Mehrnoosh Raoufi, Youtao Zhang, Jun Yang

We develop a set of techniques to reduce the memory intensity of each type while ensuring the obliviousness at the same time — we reduce the number of data blocks to access for each tree path, reduce the number of path accesses for position maps, and convert many dummy path accesses to early write-backs of dirty data in LLC.

Computer Architecture and Systems Computer Security +1

Improved Multi-step FCS-MPCC with Disturbance Compensation for PMSM Drives -- Methods and Experimental Validation

no code implementations15 May 2022 Hai Yang, Yibin Liu, Junxiao Wang, Jun Yang

In this paper, an improved multi-step finite control set model predictive current control (FCS-MPCC) strategy with speed loop disturbance compensation is proposed for permanent magnet synchronous machine (PMSM) drives system.

A distributionally robust optimization approach to two-sided chance constrained stochastic model predictive control with unknown noise distribution

no code implementations16 Mar 2022 Yuan Tan, Jun Yang, Wen-Hua Chen, Shihua Li

In this work, we propose a distributionally robust stochastic model predictive control (DR-SMPC) algorithm to address the problem of two-sided chance constrained discrete-time linear system corrupted by additive noise.

Multi-step dual control for exploration and exploitation in autonomous search with convergence guarantee

no code implementations12 Mar 2022 Yuan Tan, Jun Yang, Wen-Hua Chen, Shihua Li

Motivated by the recently proposed dual control for exploration and exploitation (DCEE) concept, this paper presents a Multi-Step DCEE (MS-DCEE) framework with guaranteed convergence for autonomous search of a source of airborne dispersion.

Next-Best-View Prediction for Active Stereo Cameras and Highly Reflective Objects

no code implementations27 Feb 2022 Jun Yang, Steven L. Waslander

Depth acquisition with the active stereo camera is a challenging task for highly reflective objects.

Depth Completion Pose Estimation

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

no code implementations15 Nov 2021 Qiyue Yin, Jun Yang, Kaiqi Huang, Meijing Zhao, Wancheng Ni, Bin Liang, Yan Huang, Shu Wu, Liang Wang

Through this survey, we 1) compare the main difficulties among different kinds of games and the corresponding techniques utilized for achieving professional human level AIs; 2) summarize the mainstream frameworks and techniques that can be properly relied on for developing AIs for complex human-computer gaming; 3) raise the challenges or drawbacks of current techniques in the successful AIs; and 4) try to point out future trends in human-computer gaming AIs.

Decision Making

Exposing Deepfake with Pixel-wise AR and PPG Correlation from Faint Signals

no code implementations29 Oct 2021 Maoyu Mao, Jun Yang

This scheme extracts two types of minute information hidden between face pixels-photoplethysmography (PPG) features and auto-regressive (AR) features, which are used as the basis for forensics in the temporal and spatial domains, respectively.

Face Swapping Photoplethysmography (PPG)

Offline Reinforcement Learning with Value-based Episodic Memory

1 code implementation ICLR 2022 Xiaoteng Ma, Yiqin Yang, Hao Hu, Qihan Liu, Jun Yang, Chongjie Zhang, Qianchuan Zhao, Bin Liang

Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data.

D4RL Offline RL +2

Safe Opponent-Exploitation Subgame Refinement

no code implementations29 Sep 2021 Mingyang Liu, Chengjie WU, Qihan Liu, Yansen Jing, Jun Yang, Pingzhong Tang, Chongjie Zhang

Search algorithms have been playing a vital role in the success of superhuman AI in both perfect information and imperfect information games.

Concurrent Active Learning in Autonomous Airborne Source Search: Dual Control for Exploration and Exploitation

no code implementations18 Aug 2021 Zhongguo Li, Wen-Hua Chen, Jun Yang

In this setting, the control action not only minimises the tracking error between future agent's position and estimated source location, but also the uncertainty of predicted estimation.

Active Learning

Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data

no code implementations16 Jul 2021 Jiandong Mu, Mengdi Wang, Feiwen Zhu, Jun Yang, Wei Lin, Wei zhang

Reinforcement learning (RL)-based auto-pruning has been further proposed to automate the DNN pruning process to avoid expensive hand-crafted work.

Neural Network Compression reinforcement-learning +2

Average-Reward Reinforcement Learning with Trust Region Methods

no code implementations7 Jun 2021 Xiaoteng Ma, Xiaohang Tang, Li Xia, Jun Yang, Qianchuan Zhao

Our work provides a unified framework of the trust region approach including both the discounted and average criteria, which may complement the framework of reinforcement learning beyond the discounted objectives.

Continuous Control reinforcement-learning +1

You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient

1 code implementation4 Jun 2021 Shaokun Zhang, Xiawu Zheng, Chenyi Yang, Yuchao Li, Yan Wang, Fei Chao, Mengdi Wang, Shen Li, Jun Yang, Rongrong Ji

Motivated by the necessity of efficient inference across various constraints on BERT, we propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere.

AutoML Model Compression

Dual-Stage Low-Complexity Reconfigurable Speech Enhancement

no code implementations17 May 2021 Jun Yang, Nico Brailovsky

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources.

Speech Enhancement

Compact Dual-Polarization Silicon Integrated Couplers for Multicore Fibers

no code implementations17 Feb 2021 Julian L. Pita Ruiz, Lucas G. Rocha, Jun Yang, Sukru Ekin Kocabas, Ming-Jun Li, Ivan Aldaya, Paulo Dainese, Lucas H. Gabrielli

Compact fiber-to-chip couplers play an important role in optical interconnections, especially in data centers.

Optics Applied Physics

Acoustic Structure Inverse Design and Optimization Using Deep Learning

no code implementations29 Jan 2021 Xuecong Sun, Han Jia, Yuzhen Yang, Han Zhao, Yafeng Bi, Zhaoyong Sun, Jun Yang

From ancient to modern times, acoustic structures have been used to control the propagation of acoustic waves.

Speech Enhancement

Phase Shift of Planetary Waves and Wave--Jet Resonance on Tidally Locked Planets

no code implementations30 Nov 2020 Shuang Wang, Jun Yang

This study improves the understanding of wave--mean flow interactions on tidally locked planets.

Atmospheric and Oceanic Physics Earth and Planetary Astrophysics Fluid Dynamics

FusionStitching: Boosting Memory Intensive Computations for Deep Learning Workloads

no code implementations23 Sep 2020 Zhen Zheng, Pengzhan Zhao, Guoping Long, Feiwen Zhu, Kai Zhu, Wenyi Zhao, Lansong Diao, Jun Yang, Wei. Lin

We show in this work that memory intensive computations can result in severe performance problems due to off-chip memory access and CPU-GPU context switch overheads in a wide range of deep learning models.

Code Generation

Active Disturbance Rejection Control Design with Suppression of Sensor Noise Effects in Application to DC-DC Buck Power Converter

no code implementations7 Sep 2020 Krzysztof Łakomy, Rafal Madonski, Bin Dai, Jun Yang, Piotr Kicki, Maral Ansari, Shihua Li

The performance of active disturbance rejection control (ADRC) algorithms can be limited in practice by high-frequency measurement noise.

Intelligent Optimization of Diversified Community Prevention of COVID-19 using Traditional Chinese Medicine

no code implementations28 Jul 2020 Yu-Jun Zheng, Si-Lan Yu, Jun-Chao Yang, Tie-Er Gan, Qin Song, Jun Yang, Mumtaz Karatas

First, we use a fuzzy clustering method to divide the population based on both modern medicine and TCM health characteristics; we then use an interactive optimization method, in which TCM experts develop different TCM prevention programs for different clusters, and a heuristic algorithm is used to optimize the programs under the resource constraints.


SOAC: The Soft Option Actor-Critic Architecture

no code implementations25 Jun 2020 Chenghao Li, Xiaoteng Ma, Chongjie Zhang, Jun Yang, Li Xia, Qianchuan Zhao

In these tasks, our approach learns a diverse set of options, each of whose state-action space has strong coherence.

Transfer Learning

Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration

1 code implementation5 Jun 2020 Ming Zhang, Yawei Wang, Xiaoteng Ma, Li Xia, Jun Yang, Zhiheng Li, Xiu Li

The generative adversarial imitation learning (GAIL) has provided an adversarial learning framework for imitating expert policy from demonstrations in high-dimensional continuous tasks.

Continuous Control Imitation Learning

DaSGD: Squeezing SGD Parallelization Performance in Distributed Training Using Delayed Averaging

no code implementations31 May 2020 Qinggang Zhou, Yawen Zhang, Pengcheng Li, Xiaoyong Liu, Jun Yang, Runsheng Wang, Ru Huang

The state-of-the-art deep learning algorithms rely on distributed training systems to tackle the increasing sizes of models and training data sets.

DSAC: Distributional Soft Actor Critic for Risk-Sensitive Reinforcement Learning

no code implementations30 Apr 2020 Xiaoteng Ma, Li Xia, Zhengyuan Zhou, Jun Yang, Qianchuan Zhao

In this paper, we present a new reinforcement learning (RL) algorithm called Distributional Soft Actor Critic (DSAC), which exploits the distributional information of accumulated rewards to achieve better performance.

Continuous Control reinforcement-learning +1

Auto-Ensemble: An Adaptive Learning Rate Scheduling based Deep Learning Model Ensembling

no code implementations25 Mar 2020 Jun Yang, Fei Wang

The advantage of this method is to make the model converge to various local optima by scheduling the learning rate in once training.

Few-Shot Learning Scheduling

Characterizing Deep Learning Training Workloads on Alibaba-PAI

no code implementations14 Oct 2019 Mengdi Wang, Chen Meng, Guoping Long, Chuan Wu, Jun Yang, Wei. Lin, Yangqing Jia

One critical issue for efficiently operating practical AI clouds, is to characterize the computing and data transfer demands of these workloads, and more importantly, the training performance given the underlying software framework and hardware configurations.

Efficient Knowledge Graph Accuracy Evaluation

no code implementations23 Jul 2019 Junyang Gao, Xi-An Li, Yifan Ethan Xu, Bunyamin Sisman, Xin Luna Dong, Jun Yang

To address the problem, this paper proposes an efficient sampling and evaluation framework, which aims to provide quality accuracy evaluation with strong statistical guarantee while minimizing human efforts.


Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks

no code implementations21 Nov 2018 Mengdi Wang, Qing Zhang, Jun Yang, Xiaoyuan Cui, Wei. Lin

In this method, the network is viewed as a computational graph, in which the vertices denote the computation nodes and edges represent the information flow.

Knowledge Distillation Model Compression

A Novel Integrated Framework for Learning both Text Detection and Recognition

no code implementations21 Nov 2018 Wanchen Sui, Qing Zhang, Jun Yang, Wei Chu

In this paper, we propose a novel integrated framework for learning both text detection and recognition.

Text Detection

Pyramid Embedded Generative Adversarial Network for Automated Font Generation

no code implementations20 Nov 2018 Donghui Sun, Qing Zhang, Jun Yang

The generator is built using one encoder-decoder structure with cascaded refinement connections and mirror skip connections.

Font Generation

FusionStitching: Deep Fusion and Code Generation for Tensorflow Computations on GPUs

no code implementations13 Nov 2018 Guoping Long, Jun Yang, Kai Zhu, Wei. Lin

In recent years, there is a surge on machine learning applications in industry.

Distributed, Parallel, and Cluster Computing Mathematical Software

Wearable Affective Robot

no code implementations25 Oct 2018 Min Chen, Jun Zhou, Guangming Tao, Jun Yang, Long Hu

The learning algorithm for the life modeling embedded in Fitbot can achieve better user's experience of affective social interaction.

Electroencephalogram (EEG) Human-Computer Interaction

Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI

1 code implementation Elsevier 2017 Xin Yang, Chaoyue Liu, Zhiwei Wang, Jun Yang, Hung Le Min, Liang Wang, Kwang-Ting (Tim) Cheng

Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions’ locations.

General Classification

NV-Tree: Reducing Consistency Cost for NVM-based Single Level Systems

no code implementations16 Apr 2015 Jun Yang, Qingsong Wei, Cheng Chen, Chundong Wang, and Khai Leong Yong, Data Storage Institute, A-STAR; Bingsheng He, Nanyang Technological University

Although the memory fence and CPU cacheline flush instructions can order memory writes to achieve data consistency, they introduce a significant overhead (more than 10X slower in performance).

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