Virtual Dimensionality of Hyperspectral Data: Use of Multiple Hypothesis Testing for Controlling Type-I Error

Vijayashekhar, S S; Bhatt, Jignesh S.; Chattopadhyay, Bhargab

doi:10.1109/jstars.2020.2991170

Cited by 15 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We select four sparse unmixing methods and a DL method to compare with the proposed IVIU-Net, including SUnSAL [20], CLSUnSAL [55], RSU [56], SUnSAL-TV [22] and Deep Autoencoder(DAE) [57]. On the tagged dataset, we refer to the method in [58] to estimate the number of endmembers, then initialize the DAE algorithm using the endmember extracted by VCA [15] and the real endmember respectively, and use it as a comparison algorithm separately. All comparison algorithms are published or provided privately by the author, and we try our best to make the results the best.…”

Section: Comparison Of Methodsmentioning

confidence: 99%

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

Shao

Liu

Xiao

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

At present, an emerging technique called the algorithm unrolling approach has attracted wide attention, because it is capable of developing efficient and interpretable layers to eliminate the black-box nature of deep learning (DL). In this paper, inspired by the sparse unmixing model, we propose a model-driven DL approach, namely, an implicit variable iterative unrolling network (IVIU-Net). First of all, the unmixing performance and adaptive ability of the model are enhanced by introducing learnable parameters into the sparse unmixing algorithm. Then, a specific spatial convolution module is integrated into the network to promote the smoothness of the latent abundance map. Finally, a comprehensive loss function with three terms such as average spectral angle distance, HSIs reconstruction error, and spectral information divergence, is presented to train the IVIU-Net in an unsupervised way. Compared to the unmixing results of most existing data-driven DL algorithms, our network has significant advantages in two folds: 1) it is able to achieve better stability instead of relying heavily on the endmember initialization results; 2) it has better interpretability and robustness in the unmixing procedure. Experimental results on synthetic and real data show that the proposed network outperforms the state-of-the-art in terms of better convergence, faster unmixing speed as well as better accuracy.

show abstract

Section: Comparison Of Methodsmentioning

confidence: 99%

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

Shao

Liu

Xiao

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In contrast, NU-BGBM, rNMF, DMBU, and the proposed approach were built based on NLMM, which considers additional interactions. In addition, the identification of endmember numbers is also an important part of blind unmixing [64], [65]. In this study, we employed the HySIME algorithm [66] to identify the number of endmembers in all experiments.…”

Section: B Description Of Other Comparison Methodsmentioning

confidence: 99%

Residual Dense Autoencoder Network for Nonlinear Hyperspectral Unmixing

Yang

Chen

Wang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Hyperspectral unmixing is a popular research topic in hyperspectral processing, aiming at obtaining the ground features contained in the mixed pixels and their proportion. Recently, nonlinear mixing models have received particular attention in hyperspectral decomposition since the linear mixing model cannot suitably apply in the situation that exists in multiple scattering. In this study, we constructed a residual dense autoencoder network (RDAE) for nonlinear hyperspectral unmixing in multiple scattering scenarios. First, an encoder was built based on the residual dense network (RDN) and attention layer. The RDN is employed to characterize multi-scale representations, which are further transformed with the attention layer to estimate the abundance maps. Second, we designed a decoder based on the unfolding of a generalized bilinear model to extract endmembers and estimate their second-order scattering interactions. Comparative experiments between the RDAE and six other state-of-the-art methods under synthetic and real hyperspectral datasets demonstrate that the proposed method achieved a better performance in terms of endmember extraction and abundance estimation.

show abstract

“…In the synthetic dataset, R is set to the quantity of endmembers in the synthetic dataset. In the real experiments, the Virtual Dimensionality (VD) [46], [47] and the HySime algorithm [48] for Minimum Error Hyperspectral Signal Subspace Identification are used to determine the number of distinct materials present in the real HSIs. We will analyze and explore the impact of these parameters (µ, λ and ξ) on the algorithm performance in section V.…”

Section: B Implementation Detailsmentioning

confidence: 99%

Hyperspectral Unmixing Using Reweighted Unidirectional TV Low-Rank NTF With Multiple-Factor Collaboration Regularization

Qu,

Li,

Luo

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The purpose of hyperspectral unmixing (HU) is to extract the spectral signatures and their proportion fractions from the hyperspectral images (HSIs), which is a crucial issue in HSIs processing. Recently, nonnegative tensor factorization (NTF) has been successfully applied in the field of HU, because a third-order tensor can effectively maintain the spatial-spectral structure of HSIs, and NTF can produce multiple-view factor matrices that can impose more natural and diverse constraints. However, current NTF unmixing models utilizing priors are still insufficient, and NTF does not fully utilize the multiview factor matrices. Moreover, most methods only consider singlefactor constraints, neglecting the effectiveness of collaborative constraints among multiple-factor priors information. To address the aforementioned shortcomings, a reweighted unidirectional total variation low-rank NTF with multiple-factor collaborative regularization is proposed. Specifically, first, to further exploit the abundance prior information, by utilizing the spatial similarity and the group sparse structure between the pixels of the two abundance low-rank sub-matrices, two reweighted unidirectional total variation (UTV) regularizers are constructed, which enhance the smooth and sparse properties of the abundances. Secondly, to smooth the endmember spectra and reduce the irregular burrs phenomenon caused by spectral noise interference, we introduce endmember band difference smooth constraints to ensure the piecewise smoothness of the endmember spectrum. Then, two reweighted UTV regularizers and an endmember spectral smooth regularizer are jointly introduced into the low-rank NTF framework to collaboratively regularize the non-convex tensor representation model. Finally, we adopt the alternating direction multiplier method (ADMM) to optimize the objective model, and a large number of experiments on both synthetic and real hyperspectral datasets validate the effectiveness and efficiency of the proposed approach.

show abstract

Virtual Dimensionality of Hyperspectral Data: Use of Multiple Hypothesis Testing for Controlling Type-I Error

Cited by 15 publications

References 35 publications

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

Residual Dense Autoencoder Network for Nonlinear Hyperspectral Unmixing

Hyperspectral Unmixing Using Reweighted Unidirectional TV Low-Rank NTF With Multiple-Factor Collaboration Regularization

Contact Info

Product

Resources

About