Hyperspectral Remote Sensing Image Feature Representation Method Based on CAE-H with Nuclear Norm Constraint

Yu, Xiaodong; Ding, Rui; Shao, Jun; Li, Xiaohui

doi:10.3390/electronics10212667

Cited by 1 publication

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This fact poses the challenge of learning better feature representation and is prone to overfitting of methods. In view of the above problems, some schemes have been proposed to alleviate them, mainly including feature extraction [21][22][23], dimension reduction [24,25], and data augmentation [26].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid 3D–2D Feature Hierarchy CNN with Focal Loss for Hyperspectral Image Classification

Wen,

Yu,

Wang

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification has been extensively applied for analyzing remotely sensed images. HSI data consist of multiple bands that provide abundant spatial information. Convolutional neural networks (CNNs) have emerged as powerful deep learning methods for processing visual data. In recent work, CNNs have shown impressive results in HSI classification. In this paper, we propose a hierarchical neural network architecture called feature extraction with hybrid spectral CNN (FE-HybridSN) to extract superior spectral–spatial features. FE-HybridSN effectively captures more spectral–spatial information while reducing computational complexity. Considering the prevalent issue of class imbalance in experimental datasets (IP, UP, SV) and real-world hyperspectral datasets, we apply the focal loss to mitigate these problems. The focal loss reconstructs the loss function and facilitates effective achievement of the aforementioned goals. We propose a framework (FEHN-FL) that combines FE-HybridSN and the focal loss for HSI classification and then conduct extensive HSI classification experiments using three remote sensing datasets: Indian Pines (IP), University of Pavia (UP), and Salinas Scene (SV). Using cross-entropy loss as a baseline, we assess the hyperspectral classification performance of various backbone networks and examine the influence of different spatial sizes on classification accuracy. After incorporating focal loss as our loss function, we not only compare the classification performance of the FE-HybridSN backbone network under different loss functions but also evaluate their convergence rates during training. The proposed classification framework demonstrates satisfactory performance compared to state-of-the-art end-to-end deep-learning-based methods, such as 2D-CNN, 3D-CNN, etc.

show abstract