Temperature scaling unmixing framework based on convolutional autoencoder

•Different degrees of sparsity constraints are imposed adaptively in deep learning networks by temperature scaling techniques.•By considering the distribution of ground objects, it has good generalization in the real scene.•The framework is a new spatial level constraint method and can be transferre...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of applied earth observation and geoinformation Ročník 129; s. 103864
Hlavní autoři: Xu, Jin, Xu, Mingming, Liu, Shanwei, Sheng, Hui, Yang, Zhiru
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.05.2024
Elsevier
Témata:
Convolutional autoencoder
design
Equal-frequency binning
extracts
Hyperspectral unmixing
methodology
remote sensing
solutions
Sparsity constraint
spatial data
temperature
Temperature scaling
Hyperspectral unmixing
Temperature scaling
Sparsity constraint
Convolutional autoencoder
Equal-frequency binning
ISSN:1569-8432, 1872-826X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Different degrees of sparsity constraints are imposed adaptively in deep learning networks by temperature scaling techniques.•By considering the distribution of ground objects, it has good generalization in the real scene.•The framework is a new spatial level constraint method and can be transferred to other convolutional autoencoder-based methods. Hyperspectral unmixing is a key technology in the development of remote sensing applications. However, since both endmembers and abundances are unknown, unmixing is a non-convex problem with a large solution space. To solve this, existing methods usually impose the same strength of sparsity constraint. However, this often does not hold in practice. Because the abundances of purer regions are generally sparse, while the abundances distribution of more mixed regions should be smoother. Temperature scaling is a technique of introducing a temperature parameter T into softmax activation function to adjust the sparsity of the output. Inspired by this, we propose a temperature scaling unmixing (TSU) framework based on convolutional autoencoder (CAE). In this framework, sparse constraints of different intensities are applied to diverse regions by considering spatial similarity of ground objects distribution while preserving the ability of CAE to extract spatial features. What is more, equal-frequency binning is adopted to guide the division of regions by similarity matrix to realize the automatic temperature parameter setting. In addition, a CAE network is designed under the TSU framework in this paper, called TSUCAE. The TSUCAE method exhibits superior accuracy compared to state-of-the-art approaches, as demonstrated through extensive comparative experiments. Furthermore, the TSU framework can be transferred to other CAE-based unmixing methods directly while keeping the network structure of these methods unchanged. Sufficient ablation experiments also prove that the transfer of framework can improve the performance of unmixing. The code is publicly available at https://github.com/UPCGIT/TSUCAE.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1569-8432
1872-826X
DOI:10.1016/j.jag.2024.103864