2022
DOI: 10.1109/lgrs.2020.3020896
|View full text |Cite
|
Sign up to set email alerts
|

Correntropy-Based Autoencoder-Like NMF With Total Variation for Hyperspectral Unmixing

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
12
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 17 publications
(12 citation statements)
references
References 21 publications
0
12
0
Order By: Relevance
“…Hence, the classical NMF model defined by the least-squares loss is sensitive to noise, leading to dramatically degrading the unmixing performance. To improve the robustness of NMF, many models have been reported based on certain metrics, including but not limited to bounded Itakura-Saito (IS) divergence [125], L 2,1 -norm regularizer [62], [113], [126], [127], CIM [90], [94], [128], [129], Cauchy function [130], and general robust loss function [131]. The bounded IS divergence was employed to address the additive, multiplicative, and mixed noises in HSIs [125].…”
Section: Robust Nmfmentioning
confidence: 99%
See 1 more Smart Citation
“…Hence, the classical NMF model defined by the least-squares loss is sensitive to noise, leading to dramatically degrading the unmixing performance. To improve the robustness of NMF, many models have been reported based on certain metrics, including but not limited to bounded Itakura-Saito (IS) divergence [125], L 2,1 -norm regularizer [62], [113], [126], [127], CIM [90], [94], [128], [129], Cauchy function [130], and general robust loss function [131]. The bounded IS divergence was employed to address the additive, multiplicative, and mixed noises in HSIs [125].…”
Section: Robust Nmfmentioning
confidence: 99%
“…Considering the diversity of the noise levels of pixels, correntropy-based spatial-spectral robust sparsity-regularized NMF (CSsRS-NMF) was proposed in [94] by adaptive assigning weights to noisy pixels. Furthermore, robustness can be achieved from an element-wise noise perspective [90], [129]. By cutting off the large error via the truncation operation, the truncated Cauchy loss [169] exhibits robustness to outliers.…”
Section: Robust Nmfmentioning
confidence: 99%
“…Specially, simplex minimum volume, abundance sparsity, and abundance smoothness have been simultaneously studied in the multiplepriors ensemble constrained NMF (MPEC-NMF) model [42]. Many other related methods, such as graph regularized based [43], self-paced based NMF algorithms [44], tensor based [45], [46], and deep learning based unmixing algorithms [47]- [49], hava also been developed. However, these algorithms do not deal well with outliers or noise and the effect on spatial structure of abundance distribution still needs to be further verified.…”
Section: Introductionmentioning
confidence: 99%
“…It is unfortunate that the facility restrictions and weather conditions lead to HSI is usually polluted by mixed noise. In addition to limiting the image quality, the existence of noise always hinders the subsequent application, such as, unmixing [4][5][6], classification Y. Chen is with the School of Computer and Information Engineering, Jiangxi Normal University, Nanchang 330022, P. R. China (email: cheny-ong1872008@163.com). [7][8][9], and fusion [10], [11].…”
Section: Introductionmentioning
confidence: 99%