Jia Wang

Jia Wang

Auto-generated profile, based on publicly available information

Jia Wang

Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 May 2021 in International Journal of Imaging Systems and Technology
Verified
Journal Article
Closed access
PDF file
JWJia Wang
Jia Wang
CLChuwen Lan
Chuwen Lan
CWCaiyong Wang
Caiyong Wang
ZGZehua Gao
Zehua Gao

13 December 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
JWJia Wang
Jia Wang
LXLiuyu Xiang
Liuyu Xiang
LLLei Liu
Lei Liu
JXJiaochong Xu
Jiaochong Xu
PLPeipei Li
Peipei Li
He ZhaofengHe Zhaofeng
He Zhaofeng
Super-resolution (SR) is a fundamental and crucial task in remote sensing. It can improve low-resolution (LR) remote sensing images and has potential benefits for downstream tasks such as remote sensing object detection and recognition. Existing remote sensing image super-resolution (RSISR) methods are trained on simulated paired datasets, in which LR images are obtained by a simple and uniform (i.e., bicubic) degradation from corresponding high-resolution (HR) images. However, since this simulated degradation usually deviates from the real degradation, the performance of the trained model is limited when applied to real scenarios. To address this issue, we construct a novel real-world remote sensing image super-resolution (RRSISR) dataset to model the real-world degradation, which exploits the imaging characteristics of the spectral camera to capture paired LR-HR images of the same scene. To ensure the precise alignment of the paired images, algorithms such as image registration, geometric correction, etc. are utilized. In addition, considering the vast amount of data involved in the RSISR task and its requirement for higher efficiency, we divide the image into patches with different restoration difficulties and propose a reference table-based patch exiting (RPE) method to efficiently reduce the computation of SR. Specifically, this method incorporates a predictor to estimate the performance of the current layer and a lookup table to decide whether to exit. Extensive experiments show that models trained on the proposed RRSISR dataset produce more realistic images than models with simulated datasets and generalize well to other satellites. We also demonstrate the efficiency of our RPE.

29 May 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
JWJia Wang
Jia Wang
PLPeipei Li
Peipei Li
LXLiuyu Xiang
Liuyu Xiang
RWRui Wang
Rui Wang
ZZZhili Zhang
Zhili Zhang
He ZhaofengHe Zhaofeng
He Zhaofeng
Face super-resolution (FSR) is a crucial step in the face analysis pipeline, achieving remarkable progress by applying deep neural networks (DNNs). However, DNN-based FSR models are not robust enough and may suffer significant performance degradation due to subtle adversarial perturbations. In addition, the high-frequency details of images restored by existing models are insufficient, especially at large upsampling factors. In this paper, we propose a frequency-aware decomposition network (FD-Net) for robust face super-resolution, which aims to defend against adversarial attacks and obtain face images with fidelity. Observing that the noise introduced by adversarial attacks is often intricately mixed with the high-frequency information of the input image, we decompose and process the features of different frequencies separately to eliminate harmful perturbations and enhance high-frequency information. Specifically, by leveraging the frequency-aware capability of empirical mode decomposition (EMD), we propose an EMD-based multi-branch structure. The framework implicitly compels different branches to adaptively extract features from distinct frequency bands, limiting the adversarial noise into decoupled components restricted to specific branches. It also improves the recovery of high-frequency information, which is conducive to producing more credible results. Furthermore, we introduce a high-frequency noise suppressor capable of randomly eliminating imperceptible noise in the high-frequency components. Quantitative and qualitative results demonstrate the superior robustness of our proposed method against adversarial attacks, showing better fidelity in image reconstruction compared to state-of-the-art FSR methods, especially for upscaling factors of 8 and 16.

7 May 2025 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
JWJia Wang
Jia Wang
SXShuhan Xia
Shuhan Xia
CZChen Zou
Chen Zou
GWGuobin Wu
Guobin Wu
He ZhaofengHe Zhaofeng
He Zhaofeng
In this paper, we propose FreqFormer, a frequency-enhanced framework for face super-resolution (FSR) that synergizes spectral decomposition and dynamic feature modulation to address Transformers' inherent low-frequency bias. Unlike existing methods, FreqFormer leverages Empirical Mode Decomposition (EMD) to decompose high-resolution (HR) images into hierarchical Intrinsic Mode Functions (IMFs), providing explicit frequency anchors for progressive high-frequency recovery. Simultaneously, a lightweight prompt module dynamically injects degradation-aware textures into Transformer blocks through learnable feature interaction, compensating for real-world distortions. This work establishes a novel framework that bridges spectral fidelity and adaptive learning, significantly advancing FSR toward high-frequency-accurate restoration. Experiments on CelebA and Helen datasets demonstrate FreqFormer's superiority, which achieves 22.42 dB PSNR on $16\times$ SR ($8\times 8 \rightarrow 128\times 128$) with higher high-frequency energy preservation than state-of-the-art methods. The framework's parameter efficiency and real-time performance enable practical deployment in security and biometric systems.

1 January 2012
Verified
Conference Paper
Closed access
JWJia Wang
Jia Wang
SHShanguo Huang
Shanguo Huang
WJWeiguo Ju
Weiguo Ju
YHYongqi He
Yongqi He
HWHongXiang Wang
HongXiang Wang
WGWanyi Gu
Wanyi Gu

27 February 2026 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
JWJingyi Wang
Jingyi Wang
JWJia Wang
Jia Wang
JGJun Gao
Jun Gao
YCYan Cao
Yan Cao
YZYang Zhai
Yang Zhai
He ZhaofengHe Zhaofeng
He Zhaofeng
Efficient coordination of heterogeneous AI chips (GPU/NPU/DCU) in data centers is crucial for Large Language Model (LLM) training, but this process is hindered by architectural mismatches, protocol fragmentation, and network partitioning. Existing solutions fail to achieve unified resource management across different chips, resulting in severe resource fragmentation and reduced allreduce efficiency. To overcome these limitations, this paper proposes the unified coordination framework UniOrch, which not only integrates three core functionalities, including hardware abstraction, software standardization, and communication coordination, but also enables the training and inference of large models across heterogeneous AI chips. UniOrch's hardware-agnostic bare-metal cloud eliminates virtualization overhead through Border Gateway Protocol Ethernet Virtual Private Network (BGP EVPN) overlay networks and gateway-based chip integration; its PyTorch-based adaptation layer masks hardware differences and reduces migration costs; the Transformer Collective Communication Library (TCCL) unifies NCCL, HCCL, and OpenMPI protocols to support seamless hybrid parallel training. Furthermore, the framework's core scheduling mechanism is the Heterogeneous Hybrid Estimation Model (HHEM), which employs a two-stage cost model combining static analysis with dynamic runtime feedback to dynamically allocate computing power based on Transformer task loads, ensuring cross-chip task synchronization, resource pooling, and dynamic allocation. Deployment verification in real-world production environments (e.g., China Construction Bank) shows that UniOrch achieves significant improvements: resource utilization of heterogeneous AI infrastructure is increased by 35%, cross-chip latency is reduced by 42%, accuracy loss in heterogeneous environments is <1.5%, the GLM-130B model achieves near-linear scalability across heterogeneous AI chips (with 116.7 tokens processed per card per second). Notably, it realizes the first cross-vendor LLM training on diversified hybrid NPU-GPU clusters with convergence error <0.8%.