Version 1
: Received: 26 July 2024 / Approved: 26 July 2024 / Online: 27 July 2024 (07:28:47 CEST)
How to cite:
Li, Y.; Zhong, J.; Xie, W.; Gamba, P. Representation Learning-Based Graph and Generative Network for Hyperspectral Small Target Detection. Preprints2024, 2024072184. https://doi.org/10.20944/preprints202407.2184.v1
Li, Y.; Zhong, J.; Xie, W.; Gamba, P. Representation Learning-Based Graph and Generative Network for Hyperspectral Small Target Detection. Preprints 2024, 2024072184. https://doi.org/10.20944/preprints202407.2184.v1
Li, Y.; Zhong, J.; Xie, W.; Gamba, P. Representation Learning-Based Graph and Generative Network for Hyperspectral Small Target Detection. Preprints2024, 2024072184. https://doi.org/10.20944/preprints202407.2184.v1
APA Style
Li, Y., Zhong, J., Xie, W., & Gamba, P. (2024). Representation Learning-Based Graph and Generative Network for Hyperspectral Small Target Detection. Preprints. https://doi.org/10.20944/preprints202407.2184.v1
Chicago/Turabian Style
Li, Y., Weiying Xie and Paolo Gamba. 2024 "Representation Learning-Based Graph and Generative Network for Hyperspectral Small Target Detection" Preprints. https://doi.org/10.20944/preprints202407.2184.v1
Abstract
Hyperspectral small target detection (HSTD) is a promising pixel-level detection task. However, due to the low contrast and imbalance number between the target and background spatially and high dimensions spectrally, it is a challenging one. To address these issues, this work proposes a representation learning-based graph and generative network for hyperspectral small target detection. The model builds a fusion network through frequency representation for HSTD, where the novel architecture incorporates irregular topological data and the spatial-spectral feature to improve its representation ability. Firstly, a graph convolutional network (GCN) module better models the non-local topological relationship between samples to represent the hyperspectral scene’s underlying data structure. The mini-batch-training pattern of the GCN decreases the high computational cost of building an adjacency matrix for high-dimensional data sets. In parallel, the generative model enhances the differentiation reconstruction and the deep feature representation ability with respect to the target spectral signature. Finally, a fusion module compensates for the extracted different types of HS features and integrates their complementary merits for hyperspectral data interpretation while increasing detection and background suppression capabilities. Experiments on different hyperspectral data sets demonstrate the advantages of the proposed architecture.
Keywords
graph convolutional network; generative adversarial network; frequency learning; representation learning; hyperspectral small target detection
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
