Xinyang Liu

Xinyang Liu

Auto-generated profile, based on publicly available information

Xinyang Liu

Hong Kong Polytechnic University, Hong Kong, Hong Kong

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
28 October 2024
Verified
Conference Paper
Open access
JHJunming Hou
Junming Hou
ZCZihan Cao
Zihan Cao
NZNaishan Zheng
Naishan Zheng
XLXuan Li
Xuan Li
XCXiaoyu Chen
Xiaoyu Chen
MZMan Zhou
Man Zhou
Vision transformer family has dominated the satellite pan-sharpening field driven by the global-wise spatial information modeling mechanism from the core self-attention ingredient. The standard modeling rules within these promising pan-sharpening methods are to roughly stack the transformer variants in a cascaded manner. Despite the remarkable advancement, their success may be at the huge cost of model parameters and FLOPs, thus preventing its application over low-resource satellites. To address this challenge between favorable performance and expensive computation, we tailor an efficient linearly-evolved transformer variant and employ it to construct a lightweight pan-sharpening framework. In detail, we deepen into the popular cascaded transformer modeling with cutting-edge methods and develop the alternative 1-order linearly-evolved transformer variant with the 1-dimensional linear convolution chain to achieve the same function. In this way, our proposed method is capable of benefiting the cascaded modeling rule while achieving favorable performance in the efficient manner. Extensive experiments over multiple satellite datasets suggest that our proposed method achieves competitive performance against other state-of-the-art with fewer computational resources. Further, the consistently favorable performance has been verified over the hyper-spectral image fusion task. Our main focus is to provide an alternative global modeling framework with an efficient structure. The code is publicly available at https://github.com/coder-JMHou/LFormer.

13 January 2025 in Information Fusion
Verified
Journal Article
Closed access
JHJunming Hou
Junming Hou
XLXinyang Liu
Xinyang Liu
CWChenxu Wu
Chenxu Wu
XCXiaofeng Cong
Xiaofeng Cong
CHChentong Huang
Chentong Huang
JYJian Wei You
Jian Wei You

7 December 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XLXinyang Liu
Xinyang Liu
JHJunming Hou
Junming Hou
XCXiaofeng Cong
Xiaofeng Cong
HSHao Shen
Hao Shen
ZLZhuochen Lou
Zhuochen Lou
JYJian Wei You
Jian Wei You
Pan-sharpening aims to super-resolve the low-resolution (LR) multi-spectral (MS) image under the guidance of high-resolution (HR) panchromatic (PAN) image. Existing deep learning-based pan-sharpening methods usually adhere to a common philosophy of learning complementary information between MS and PAN images. Despite remarkable advances, few studies consider the band-private characteristics which differ greatly from band to band. An ideal MS image, however, is jointly determined by its diverse spectral bands, thus the accurate restoration of every band will benefit the pan-sharpening performance. In this work, we propose a novel yet effective solution to reconstruct HRMS image by explicitly modulating every spectral band, conditioning on the PAN image. As a result, we design a spatially-adaptive spectral modulation network, dubbed SSMNet, which consists of three core designs: source-adaptive spectral modulator (SSM), cross-band information aggregation (CBIA) module, and cross-stage feature integration (CSFI) module. The first predicts a series of spatially-adaptive kernels to capture the local information of every spectral band. Followed by, the second is responsible for facilitating the information communication among various bands to guarantee the continuous spectral representations. Furthermore, the third attends to integrate the cross-stage output features to produce the pan-sharpened result. In addition, we also introduce the histogram loss to constrain the band-wise distribution of the final fused products. Extensive experiments demonstrate that our SSMNet achieves the favorable performance against other state-of-the-art methods on multiple satellite datasets. The code is available at https://github.com/ez4lionky/SSMNet/.

1 January 2008
Verified
Book Chapter
Open access
PDF file
XLXinyang Liu
Xinyang Liu
WMWashington Mio
Washington Mio
YSYonggang Shi
Yonggang Shi
IDIvo D. Dinov
Ivo D. Dinov
XLXiuwen Liu
Xiuwen Liu
PTPaul M. Thompson
Paul M. Thompson
We develop a model of continuous spherical shapes and use it to analyze the anatomy of the hippocampus. To account for the geometry of bends and folds, the model relies on a geodesic metric that is sensitive to first-order deformations. We construct an atlas of the hippocampus as a mean shape and develop statistical models to characterize quantitative and qualitative normal shape variation. We also develop a localization tool to identify local contrasts in the anatomy of different populations. The tool is applied to the detection, characterization and visualization of anatomical differences such as local enlargement and gains in volume on the right hippocampus of blind subjects.

4 July 2025 in Neurocomputing
Verified
Journal Article
Closed access
BLBo Liu
Bo Liu
XLXinyang Liu
Xinyang Liu
CCChang Chen
Chang Chen
JHJianwei Huang
Jianwei Huang
ZDZhengtao Ding
Zhengtao Ding