Zhi Li

Zhi Li

Auto-generated profile, based on publicly available information

Zhi Li

Key Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
20 January 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Jiaxin 李嘉鑫 LiJiaxin 李嘉鑫 Li
Jiaxin 李嘉鑫 Li
KZKe Zheng
Ke Zheng
LGLianru Gao
Lianru Gao
Zhu HanZhu Han
Zhu Han
ZLZhi Li
Zhi Li
Jocelyn  ChanussotJocelyn Chanussot
Jocelyn Chanussot
Depending on a large-scale paired dataset of low-resolution hyperspectral images (LrHSI), high-resolution multispectral images (HrMSI), and corresponding high-resolution hyperspectral images (HrHSI), the supervised paradigm has achieved impressive performance in the hyperspectral image super-resolution (HISR). However, the intrinsic data-intensive manner hinders its further application in real scenarios. Fortunately, deep image prior (DIP) allows us to achieve unsupervised SR by solely utilizing degraded observations. However, its potential to accurately model complicated hyperspectral priors is still not fully exploited owing to the following two factors: i) Existing methods tend to reconstruct the unknown HrHSI directly from a randomly generated noise, leaving it hard to leverage the scene-relevant information for prior learning; ii) The vanilla architecture is handcrafted for the generator network, which shows limitations in feature representation and hence fails to characterize the complicated image properties. To unleash the potential of DIP for the HISR task, we propose an enhanced DIP network, called EDIP-Net, by addressing the aforementioned impediments. Specifically, EDIP-Net is built with a two-stage four-component scheme, with a zero-shot learning (ZSL) stage for input image establishment and a deep image generation stage for prior learning. First, we exploit the cross-scale spectral relationship inside the observations and hence design a degradation learning network to generate paired training samples from the observations themselves. As such, two image-coarse estimations are derived in a ZSL manner by learning an interactive spectral learning network. By replacing random noise with two estimations, we design a double U-shape architecture for the generator network to capture their hyperspectral prior, each independently generating one HrHSI candidate. Under this premise, we further propose a degradation-aware decision fusion strategy to integrate the optimal results in a pixel-to-pixel manner. Extensive experiments demonstrate our superiority in achieving high-quality SR performance. The code will be available at https://github.com/JiaxinLiCAS.

11 July 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
ZLZhi Li
Zhi Li
KZKe Zheng
Ke Zheng
Jiaxin 李嘉鑫 LiJiaxin 李嘉鑫 Li
Jiaxin 李嘉鑫 Li
CLChengrui Li
Chengrui Li
LGLianru Gao
Lianru Gao
The adequate and finer spectral information in hyperspectral images (HSIs) are benefit for various downstream applications like smart agriculture and environmental monitoring. In HSI classification, dual-stream convolutional networks have gained much attention and have been widely used. In patch-based hyperspectral classification tasks, however, merely using center-labeled patches could lead to an increased unlabeled noise in the data. Moreover, in the application of dual-stream network structures, heterogeneity existed in both the data and feature semantic levels to capture more representative features. To tackle these challenges, we have devised a framework called cross-semantic heterogeneous modeling network (CreatingNet), which aligns more closely with the design principles of dual-stream networks by adjusting the input size. This framework introduces a distance metric attention mechanism (DMAM) based on spectral and spatial distances to strengthen the influence of the center pixel on the entire patch. Additionally, we present a fusion module named CrossViT, which combines features with diverse structures and characteristics, leveraging their complementarity. The proposed multiscale heterogeneous fusion module allows for more effective integration of spatial and spectral features in the images. Extensive experiments on four well-known HSI datasets (Indian Pines, Pavia University, Salinas, and Houston 2013) demonstrate the superior classification performance of the proposed CreatingNet to several state-of-the-art methods. The effectiveness of the proposed model is further validated through ablation studies.

18 April 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
ZLZhi Li
Zhi Li
KZKe Zheng
Ke Zheng
LGLianru Gao
Lianru Gao
NZNannan Zi
Nannan Zi
CLChengrui Li
Chengrui Li
Deep learning has become increasingly popular in hyperspectral image (HSI) and light detection and ranging (LiDAR) data classification, thanks to its powerful feature learning and representation capabilities. However, HSI often contains substantial redundant information, which can hinder efficient data utilization. Furthermore, the significant disparity in information content between HSI and LiDAR data poses a major challenge in representing and aligning semantic information across these two modalities. To address these challenges, we propose a fusion network structure guided by feature reconstruction embedding. This approach employs feature decomposition to reconstruct HSI features and incorporates weight embedding to seamlessly integrate the reconstructed information into classification features. Furthermore, we introduce a cross-modal attention fusion module designed to merge extracted HSI and LiDAR features. This module fully exploits the complementary nature of these two type of feature, facilitating effective information exchange and semantic alignment across multimodal data. We evaluated our method on three widely used HSI and LiDAR datasets: Houston 2013, Augsburg and MUUFL. Experimental results demonstrate that our proposed FRGFNet significantly outperforms traditional probabilistic methods and state-of-the-art deep learning networks, showcasing its effectiveness in multi-source data fusion.

27 August 2024 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
Zhu HanZhu Han
Zhu Han
SXShuyi Xu
Shuyi Xu
LGLianru Gao
Lianru Gao
ZLZhi Li
Zhi Li
Bing ZhangBing Zhang
Bing Zhang
Vision transformer (ViT) is a prevalent technique for capturing long-distance dependencies and has shown impressive performance in the field of hyperspectral image (HSI) classification. However, the core component of ViT, namely self-attention, faces challenges in balancing high computational complexity and global modeling within entire input sequences. To alleviate this issue, a novel Gaussian retentive network, called GRetNet, is devised in this letter to enhance the comprehension of fine-grained spatial and spectral features while reducing computational costs. This method provides a powerful classification backbone and can adaptively generate priors to perceive more effective spatial information by introducing a spatial decay mask to assign different weights at various positions. Furthermore, the Gaussian multi-head attention is designed to provide dynamic recalibration of feature significance based on statistical distribution and focuses on distinct spectral patterns across different heads, thereby rendering a more concise and robust modeling for HSI classification. Compared with the state-of-the-art classification algorithms, the proposed GRetNet method can yield better classification results and computational efficiency on four benchmark hyperspectral datasets, which verifies its effectiveness and superiority.