Hyperspectral Image
Hyperspectral imaging (HSI) captures detailed spectral information across numerous bands, enabling precise material identification and scene analysis beyond the capabilities of traditional RGB or multispectral imaging. Current research heavily focuses on improving HSI classification and reconstruction using advanced deep learning architectures, such as transformers and state-space models (SSMs), often incorporating spatial context and addressing challenges like computational efficiency and data scarcity through techniques like self-supervised learning and test-time training. These advancements have significant implications for diverse fields, including remote sensing, precision agriculture, medical imaging, and environmental monitoring, offering enhanced capabilities for material identification, object detection, and scene understanding.
Papers
C$^3$DG: Conditional Domain Generalization for Hyperspectral Imagery Classification with Convergence and Constrained-risk Theories
Zhe Gao, Bin Pan, Zhenwei Shi
Adaptive Step-size Perception Unfolding Network with Non-local Hybrid Attention for Hyperspectral Image Reconstruction
Yanan Yang, Like Xin
Orthogonal Constrained Minimization with Tensor $\ell_{2,p}$ Regularization for HSI Denoising and Destriping
Xiaoxia Liu, Shijie Yu, Jian Lu, Xiaojun Chen
Evaluation of Deep Learning Semantic Segmentation for Land Cover Mapping on Multispectral, Hyperspectral and High Spatial Aerial Imagery
Ilham Adi Panuntun, Ying-Nong Chen, Ilham Jamaluddin, Thi Linh Chi Tran
Boosting Hyperspectral Image Classification with Gate-Shift-Fuse Mechanisms in a Novel CNN-Transformer Approach
Mohamed Fadhlallah Guerri, Cosimo Distante, Paolo Spagnolo, Fares Bougourzi, Abdelmalik Taleb-Ahmed
CMTNet: Convolutional Meets Transformer Network for Hyperspectral Images Classification
Faxu Guo, Quan Feng, Sen Yang, Wanxia Yang