Search Results for author: Xiao-Ping Zhang

Found 57 papers, 13 papers with code

OpenCarbonEval: A Unified Carbon Emission Estimation Framework in Large-Scale AI Models

no code implementations21 May 2024 Zhaojian Yu, Yinghao Wu, Zhuotao Deng, Yansong Tang, Xiao-Ping Zhang

By promoting sustainable AI development and deployment, OpenCarbonEval can help reduce the environmental impact of large-scale models and contribute to a more environmentally responsible future for the AI community.

RSHazeDiff: A Unified Fourier-aware Diffusion Model for Remote Sensing Image Dehazing

1 code implementation15 May 2024 Jiamei Xiong, Xuefeng Yan, Yongzhen Wang, Wei Zhao, Xiao-Ping Zhang, Mingqiang Wei

Since remote sensing images contain extensive small-scale texture structures, it is important to effectively restore image details from hazy images.

Denoising Image Dehazing +1

FL-TAC: Enhanced Fine-Tuning in Federated Learning via Low-Rank, Task-Specific Adapter Clustering

no code implementations23 Apr 2024 Siqi Ping, Yuzhu Mao, Yang Liu, Xiao-Ping Zhang, Wenbo Ding

Although large-scale pre-trained models hold great potential for adapting to downstream tasks through fine-tuning, the performance of such fine-tuned models is often limited by the difficulty of collecting sufficient high-quality, task-specific data.

Clustering Federated Learning

THQA: A Perceptual Quality Assessment Database for Talking Heads

1 code implementation13 Apr 2024 Yingjie Zhou, ZiCheng Zhang, Wei Sun, Xiaohong Liu, Xiongkuo Min, Zhihua Wang, Xiao-Ping Zhang, Guangtao Zhai

In the realm of media technology, digital humans have gained prominence due to rapid advancements in computer technology.

Video Quality Assessment

Social Physics Informed Diffusion Model for Crowd Simulation

1 code implementation8 Feb 2024 Hongyi Chen, Jingtao Ding, Yong Li, Yue Wang, Xiao-Ping Zhang

In this paper, we propose a social physics-informed diffusion model named SPDiff to mitigate the above gap.

Denoising Physics-informed machine learning

Few-Shot Class-Incremental Learning with Prior Knowledge

1 code implementation2 Feb 2024 Wenhao Jiang, Duo Li, Menghan Hu, Guangtao Zhai, Xiaokang Yang, Xiao-Ping Zhang

To tackle the issues of catastrophic forgetting and overfitting in few-shot class-incremental learning (FSCIL), previous work has primarily concentrated on preserving the memory of old knowledge during the incremental phase.

Few-Shot Class-Incremental Learning Incremental Learning

Growing from Exploration: A self-exploring framework for robots based on foundation models

no code implementations24 Jan 2024 Shoujie Li, Ran Yu, Tong Wu, JunWen Zhong, Xiao-Ping Zhang, Wenbo Ding

In this work, we propose a framework named GExp, which enables robots to explore and learn autonomously without human intervention.

Few-Shot Learning

Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning

1 code implementation9 Jan 2024 Kuo Yang, Duo Li, Menghan Hu, Guangtao Zhai, Xiaokang Yang, Xiao-Ping Zhang

This approach allows the model to perceive the uncertainty of pseudo-labels at different training stages, thereby adaptively adjusting the selection thresholds for different classes.

Pseudo Label

Federated PAC-Bayesian Learning on Non-IID data

no code implementations13 Sep 2023 Zihao Zhao, Yang Liu, Wenbo Ding, Xiao-Ping Zhang

Existing research has either adapted the Probably Approximately Correct (PAC) Bayesian framework for federated learning (FL) or used information-theoretic PAC-Bayesian bounds while introducing their theorems, but few considering the non-IID challenges in FL.

Federated Learning

Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer

1 code implementation ICCV 2023 Guangyi Chen, Xiao Liu, Guangrun Wang, Kun Zhang, Philip H. S. Torr, Xiao-Ping Zhang, Yansong Tang

To bridge these gaps, in this paper, we propose Tem-Adapter, which enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner.

Decoder Question Answering +1

Cooperative Multi-Type Multi-Agent Deep Reinforcement Learning for Resource Management in Space-Air-Ground Integrated Networks

no code implementations8 Aug 2023 Hengxi Zhang, Huaze Tang, Wenbo Ding, Xiao-Ping Zhang

The Space-Air-Ground Integrated Network (SAGIN), integrating heterogeneous devices including low earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and ground users (GUs), holds significant promise for advancing smart city applications.


AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategy

no code implementations1 Aug 2023 Zihao Zhao, Yuzhu Mao, Zhenpeng Shi, Yang Liu, Tian Lan, Wenbo Ding, Xiao-Ping Zhang

In response, this paper introduces AQUILA (adaptive quantization in device selection strategy), a novel adaptive framework devised to effectively handle these issues, enhancing the efficiency and robustness of FL.

Federated Learning Privacy Preserving +1

Blind Image Quality Assessment: A Fuzzy Neural Network for Opinion Score Distribution Prediction

1 code implementation IEEE Transactions on Circuits and Systems for Video Technology 2023 Yixuan Gao, Xiongkuo Min, Yucheng Zhu, Xiao-Ping Zhang, Guangtao Zhai

On the other hand, we also prove the feasibility of the proposed method in predicting the MOS of image quality on several popular IQA databases, including CSIQ, TID2013, LIVE MD, and LIVE Challenge.

Blind Image Quality Assessment

Language-free Compositional Action Generation via Decoupling Refinement

1 code implementation7 Jul 2023 Xiao Liu, Guangyi Chen, Yansong Tang, Guangrun Wang, Xiao-Ping Zhang, Ser-Nam Lim

Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation.

Action Generation

Don't worry about mistakes! Glass Segmentation Network via Mistake Correction

no code implementations21 Apr 2023 Chengyu Zheng, Peng Li, Xiao-Ping Zhang, Xuequan Lu, Mingqiang Wei

The IS is designed to simulate the detection procedure of human recognition for identifying transparent glass by global context and edge information.

Optimizing Trading Strategies in Quantitative Markets using Multi-Agent Reinforcement Learning

no code implementations15 Mar 2023 Hengxi Zhang, Zhendong Shi, Yuanquan Hu, Wenbo Ding, Ercan E. Kuruoglu, Xiao-Ping Zhang

Quantitative markets are characterized by swift dynamics and abundant uncertainties, making the pursuit of profit-driven stock trading actions inherently challenging.

Decision Making Multi-agent Reinforcement Learning +2

Finding the Most Transferable Tasks for Brain Image Segmentation

no code implementations3 Jan 2023 Yicong Li, Yang Tan, Jingyun Yang, Yang Li, Xiao-Ping Zhang

Furthermore, within the same modality, transferring from the source task that has stronger RoI shape similarity with the target task can significantly improve the final transfer performance.

Brain Image Segmentation Image Segmentation +3

Visual-tactile Fusion for Transparent Object Grasping in Complex Backgrounds

no code implementations30 Nov 2022 Shoujie Li, Haixin Yu, Wenbo Ding, Houde Liu, Linqi Ye, Chongkun Xia, Xueqian Wang, Xiao-Ping Zhang

Here, a visual-tactile fusion framework for transparent object grasping under complex backgrounds and variant light conditions is proposed, including the grasping position detection, tactile calibration, and visual-tactile fusion based classification.

Classification Position +1

Segmented Learning for Class-of-Service Network Traffic Classification

1 code implementation3 Aug 2022 Yoga Suhas Kuruba Manjunath, Sihao Zhao, Hatem Abou-zeid, Akram Bin Sediq, Ramy Atawia, Xiao-Ping Zhang

The commonality of statistical features among the network flow segments motivates us to propose novel segmented learning that includes essential vector representation and a simple-segment method of classification.

Classification Scheduling +1

Transferability-Guided Cross-Domain Cross-Task Transfer Learning

no code implementations12 Jul 2022 Yang Tan, Enming Zhang, Yang Li, Shao-Lun Huang, Xiao-Ping Zhang

We propose two novel transferability metrics F-OTCE (Fast Optimal Transport based Conditional Entropy) and JC-OTCE (Joint Correspondence OTCE) to evaluate how much the source model (task) can benefit the learning of the target task and to learn more transferable representations for cross-domain cross-task transfer learning.

Transfer Learning

Dual Vision Transformer

1 code implementation11 Jul 2022 Ting Yao, Yehao Li, Yingwei Pan, Yu Wang, Xiao-Ping Zhang, Tao Mei

Dual-ViT is henceforth able to reduce the computational complexity without compromising much accuracy.

Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning

1 code implementation6 Apr 2022 Yiyang Shen, Mingqiang Wei, Sen Deng, Wenhan Yang, Yongzhen Wang, Xiao-Ping Zhang, Meng Wang, Jing Qin

To bridge the two domain gaps, we propose a semi-supervised detail-recovery image deraining network (Semi-DRDNet) with dual sample-augmented contrastive learning.

Contrastive Learning Rain Removal

SAFARI: Sparsity enabled Federated Learning with Limited and Unreliable Communications

no code implementations5 Apr 2022 Yuzhu Mao, Zihao Zhao, Meilin Yang, Le Liang, Yang Liu, Wenbo Ding, Tian Lan, Xiao-Ping Zhang

It is demonstrated that SAFARI under unreliable communications is guaranteed to converge at the same rate as the standard FedAvg with perfect communications.

Federated Learning Sparse Learning

Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds

1 code implementation23 Mar 2022 Haoran Zhou, Honghua Chen, Yingkui Zhang, Mingqiang Wei, Haoran Xie, Jun Wang, Tong Lu, Jing Qin, Xiao-Ping Zhang

Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations.

Parameterized Image Quality Score Distribution Prediction

no code implementations2 Mar 2022 Yixuan Gao, Xiongkuo Min, Wenhan Zhu, Xiao-Ping Zhang, Guangtao Zhai

Experimental results verifythe feasibility of using alpha stable model to describe the IQSD, and prove the effectiveness of objective alpha stable model basedIQSD prediction method.


Sequential Doppler Shift based Optimal Localization and Synchronization with TOA

no code implementations14 Feb 2022 Sihao Zhao, Ningyan Guo, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu

In this paper, we develop a new optimal LAS method in the TDBS, namely LAS-SDT, by taking advantage of the sequential Doppler shift and TOA measurements.

Closed-form Two-way TOA Localization and Synchronization for User Devices with Motion and Clock Drift

no code implementations13 Nov 2021 Sihao Zhao, Ningyan Guo, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu

Numerical results in a 3D scenario verify the theoretical analysis that the estimation accuracy of the new CFTWLAS method reaches CRLB in the presented experiments when the number of the ANs is large, the geometry is appropriate, and the noise is small.

Time-Distributed Feature Learning in Network Traffic Classification for Internet of Things

no code implementations29 Sep 2021 Yoga Suhas Kuruba Manjunath, Sihao Zhao, Xiao-Ping Zhang

The network traffic classification (NTC) is an essential tool to explore behaviours of network flows, and NTC is required for Internet service providers (ISPs) to manage the performance of the IoT network.

Traffic Classification

Virtual Reality Gaming on the Cloud: A Reality Check

no code implementations21 Sep 2021 Sihao Zhao, Hatem Abou-zeid, Ramy Atawia, Yoga Suhas Kuruba Manjunath, Akram Bin Sediq, Xiao-Ping Zhang

To the best of the authors' knowledge, this is the first measurement study and analysis conducted using a commercial cloud VR gaming platform, and under both fixed and adaptive bitrate streaming.


Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

no code implementations15 Jun 2021 Sen Deng, Yidan Feng, Mingqiang Wei, Haoran Xie, Yiping Chen, Jonathan Li, Xiao-Ping Zhang, Jing Qin

Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image.

Single Image Deraining

Exploiting Relationship for Complex-scene Image Generation

no code implementations1 Apr 2021 Tianyu Hua, Hongdong Zheng, Yalong Bai, Wei zhang, Xiao-Ping Zhang, Tao Mei

Our method tends to synthesize plausible layouts and objects, respecting the interplay of multiple objects in an image.

Image Generation Scene Generation

A New TOA Localization and Synchronization System with Virtually Synchronized Periodic Asymmetric Ranging Network

no code implementations17 Mar 2021 Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu

In this article, we design a new time-of-arrival (TOA) system for simultaneous user device (UD) localization and synchronization with a periodic asymmetric ranging network, namely PARN.

Semidefinite Programming Two-way TOA Localization for User Devices with Motion and Clock Drift

no code implementations3 Mar 2021 Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu

In two-way time-of-arrival (TOA) systems, a user device (UD) obtains its position by round-trip communications to a number of anchor nodes (ANs) at known locations.

Non-local Channel Aggregation Network for Single Image Rain Removal

no code implementations3 Mar 2021 Zhipeng Su, Yixiong Zhang, Xiao-Ping Zhang, Feng Qi

Second, aggregating channels could help our model to concentrate on channels more related to image background instead of rain streaks.

Rain Removal

New Closed-form Joint Localization and Synchronization using Sequential One-way TOAs

no code implementations30 Jan 2021 Ningyan Guo, Sihao Zhao, Xiao-Ping Zhang, Zheng Yao, Xiaowei Cui, Mingquan Lu

Compared with the conventional iterative method, the proposed new CFJLAS method does not require initialization, obtains the optimal solution under the small noise condition, and has a low computational complexity.

A Closed-form Localization Method Utilizing Pseudorange Measurements from Two Non-synchronized Positioning Systems

no code implementations25 Nov 2020 Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu

Numerical results verify the theoretical analysis on positioning accuracy, and show that the new CDL method has superior performance over the state-of-the-art closed-form method.

Optimal Two-way TOA Localization and Synchronization for Moving User Devices with Clock Drift

no code implementations24 Nov 2020 Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu

We show that the conventional two-way TOA method is a special case of the TWLAS when the UD is stationary, and the TWLAS has high estimation accuracy than the conventional one-way TOA method.


Claw U-Net: A Unet-based Network with Deep Feature Concatenation for Scleral Blood Vessel Segmentation

no code implementations20 Oct 2020 Chang Yao, Jingyu Tang, Menghan Hu, Yue Wu, Wenyi Guo, Qingli Li, Xiao-Ping Zhang

Sturge-Weber syndrome (SWS) is a vascular malformation disease, and it may cause blindness if the patient's condition is severe.

Identification of deep breath while moving forward based on multiple body regions and graph signal analysis

no code implementations20 Oct 2020 Yunlu Wang, Cheng Yang, Menghan Hu, Jian Zhang, Qingli Li, Guangtao Zhai, Xiao-Ping Zhang

This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera.

Change Detection in Heterogeneous Optical and SAR Remote Sensing Images via Deep Homogeneous Feature Fusion

no code implementations8 Apr 2020 Xiao Jiang, Gang Li, Yu Liu, Xiao-Ping Zhang, You He

To solve this problem, this paper presents a new homogeneous transformation model termed deep homogeneous feature fusion (DHFF) based on image style transfer (IST).

Change Detection Style Transfer

Dynamic Spatiotemporal Graph Neural Network with Tensor Network

no code implementations12 Mar 2020 Chengcheng Jia, Bo Wu, Xiao-Ping Zhang

Dynamic spatial graph construction is a challenge in graph neural network (GNN) for time series data problems.

graph construction Time Series +1

Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner

no code implementations12 Feb 2020 Yunlu Wang, Menghan Hu, Qingli Li, Xiao-Ping Zhang, Guangtao Zhai, Nan Yao

During the epidemic prevention and control period, our study can be helpful in prognosis, diagnosis and screening for the patients infected with COVID-19 (the novel coronavirus) based on breathing characteristics.

Point cloud denoising based on tensor Tucker decomposition

no code implementations20 Feb 2019 Jianze Li, Xiao-Ping Zhang, Tuan Tran

In this paper, we propose a new algorithm for point cloud denoising based on the tensor Tucker decomposition.


Interactive Binary Image Segmentation with Edge Preservation

no code implementations10 Sep 2018 Jianfeng Zhang, Liezhuo Zhang, Yuankai Teng, Xiao-Ping Zhang, Song Wang, Lili Ju

Binary image segmentation plays an important role in computer vision and has been widely used in many applications such as image and video editing, object extraction, and photo composition.

Image Segmentation Interactive Segmentation +4

Multimodal Fusion via a Series of Transfers for Noise Removal

no code implementations22 Jan 2017 Chang-Hwan Son, Xiao-Ping Zhang

Different from conventional fusion approaches, the proposed method conducts a series of transfers: contrast, detail, and color transfers.

Rain Removal via Shrinkage-Based Sparse Coding and Learned Rain Dictionary

no code implementations3 Oct 2016 Chang-Hwan Son, Xiao-Ping Zhang

Based on this error map, both the sparse codes of rain and non-rain dictionaries are used jointly to represent the image structures of objects and avoid the edge artifacts in the non-rain regions.

Dictionary Learning Image Restoration +1

Rain structure transfer using an exemplar rain image for synthetic rain image generation

no code implementations3 Oct 2016 Chang-Hwan Son, Xiao-Ping Zhang

Next, residual rain patches are selected randomly, and then added to the given target image along a raster scanning direction.

Image Generation Rain Removal

Near-Infrared Coloring via a Contrast-Preserving Mapping Model

no code implementations3 Oct 2016 Chang-Hwan Son, Xiao-Ping Zhang

This paper introduces a new coloring method to add colors to near-infrared gray images based on a contrast-preserving mapping model.

Denoising Image Restoration

Near-Infrared Image Dehazing Via Color Regularization

no code implementations1 Oct 2016 Chang-Hwan Son, Xiao-Ping Zhang

It is also shown that the proposed color regularization can remove the edge artifacts which arise from the use of the conventional dark prior model.

Image Dehazing

A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation

no code implementations CVPR 2016 Xueyang Fu, Delu Zeng, Yue Huang, Xiao-Ping Zhang, Xinghao Ding

We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image.

Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI

no code implementations12 Feb 2013 Yue Huang, John Paisley, Qin Lin, Xinghao Ding, Xueyang Fu, Xiao-Ping Zhang

The size of the dictionary and the patch-specific sparsity pattern are inferred from the data, in addition to other dictionary learning variables.

Denoising Dictionary Learning +2

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