Adversarial Autoencoder Network for Hyperspectral Unmixing

Jin, Qiwen; Ma, Yong; Fan, Fan; Huang, Jun; Mei, Xiaoguang; Ma, Jiayi

doi:10.1109/tnnls.2021.3114203

Cited by 49 publications

(17 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They impose restrictions on the encoder to be able to invert the mixing process by making use of the pseudoinverse of the endmember matrix, with both encoder and decoder being composed of sequential fully-connected layers. Another set of autoencoder techniques for unmixing is based on adversarial training, such as in [26]. It is based on the assumption that pixels in the same region share the same statistical properties and can be modeled with a prior distribution.…”

Section: Nonlinear Models Using Autoencodersmentioning

confidence: 99%

End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing

et al. 2022

View full text Add to dashboard Cite

Hyperspectral Unmixing is the process of decomposing a mixed pixel into its pure materials (endmembers) and estimating their corresponding proportions (abundances). Although linear unmixing models are more common due to their simplicity and flexibility, they suffer from many limitations in real world scenes where interactions between pure materials exist, which paved the way for nonlinear methods to emerge. However, existing methods for nonlinear unmixing require prior knowledge or an assumption about the type of nonlinearity, which can affect the results. This paper introduces a nonlinear method with a novel deep convolutional autoencoder for blind unmixing. The proposed framework consists of a deep encoder of successive small size convolutional filters along with max pooling layers, and a decoder composed of successive 2D and 1D convolutional filters. The output of the decoder is formed of a linear part and an additive non-linear one. The network is trained using the mean squared error loss function. Several experiments were conducted to evaluate the performance of the proposed method using synthetic and real airborne data. Results show a better performance in terms of abundance and endmembers estimation compared to several existing methods.

show abstract

Section: Nonlinear Models Using Autoencodersmentioning

confidence: 99%

End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing

et al. 2022

View full text Add to dashboard Cite

show abstract

“…There are three methods based on manifold learning: isometric feature mapping (ISOMAP) (Moradzadeh et al, 2020), multidimensional dimension transformation (MDT) (Leprince et al, 2021), local linear embedding (LLE), laplacian eigenmaps (LE), etc. The neural network methods include autoencoder networks (AN) (Jin et al, 2021) and self-organizing feature mapping (SOM) (Ghahramani et al, 2021). Different principles and structures of each dimension reduction algorithm will bring different recognition effects.…”

Section: Emotion Feature Dimension Reductionmentioning

confidence: 99%

Dance emotion recognition based on linear predictive Meir frequency cepstrum coefficient and bidirectional long short-term memory from robot environment

Shen

Xiao-xi²,

Jiang³

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

Dance emotion recognition is an important research direction of automatic speech recognition, especially in the robot environment. It is an important research content of dance emotion recognition to extract the features that best represent speech emotion and to construct an acoustic model with strong robustness and generalization. The dance emotion data set is small in size and high in dimension. The traditional recurrent neural network (RNN) has the problem of long-range dependence disappearance, and due to the focus on local information of convolutional neural network (CNN), the mining of potential relationships between frames in the input sequence is insufficient. To solve the above problems, this paper proposes a novel linear predictive Meir frequency cepstrum coefficient and bidirectional long short-term memory (LSTM) for dance emotion recognition. In this paper, the linear prediction coefficient (LPC) and Meier frequency cepstrum coefficient (MFCC) are combined to obtain a new feature, namely the linear prediction Meier frequency cepstrum coefficient (LPMFCC). Then, the combined feature obtained by combining LPMFCC with energy feature is used as the extracted dance feature. The extracted features are input into the bidirectional LSTM network for training. Finally, support vector machine (SVM) is used to classify the obtained features through the full connection layer. Finally, we conduct experiments on public data sets and obtain the better effectiveness compared with the state-of-art dance motion recognition methods.

show abstract

“…The first stage network estimates the endmembers and abundance maps of the input image while the second stage reconstructs the input image. In [43], autoencoders that have been used for hyperspectral unmixing are grouped into five different categories: (a) Sparse nonnegative autoencoders (a stack of nonnegative sparse autoencoders (SNSA)) [44] (b) Variational autoencoders (Deep AutoEncoder Network (DAEN) [45], Deep Generative Unmixing algorithm (DeepGUn) [46] (c) Adversarial autoencoders (Adversarial autoencoder network (AAENet)) [47]- [49] (d) Denoising autoencoders (an untied Denoising Autoencoder with Sparsity (uDAS)) [50], and (e) Convolutional autoencoders [51]- [53]. In [54], a two-stream Siamese deep network was proposed to enhance the performance of spectral unmixing.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Unmixing Using Transformer Network

Ghosh¹,

Roy²,

Koirala

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Transformers have intrigued the vision research community with their state-of-the-art performance in natural language processing. With their superior performance, transformers have found their way in the field of hyperspectral image classification and achieved promising results. In this article, we harness the power of transformers to conquer the task of hyperspectral unmixing and propose a novel deep neural network-based unmixing model with transformers. A transformer network captures nonlocal feature dependencies by interactions between image patches, which are not employed in CNN models, and hereby has the ability to enhance the quality of the endmember spectra and the abundance maps. The proposed model is a combination of a convolutional autoencoder and a transformer. The hyperspectral data is encoded by the convolutional encoder. The transformer captures long-range dependencies between the representations derived from the encoder. The data are reconstructed using a convolutional decoder. We applied the proposed unmixing model to three widely used unmixing datasets, i.e., Samson, Apex, and Washington DC mall and compared it with the state-of-the-art in terms of root mean squared error and spectral angle distance. The source code for the proposed model will be made publicly available at https://github.com/preetam22n/DeepTrans-HSU.

show abstract

Adversarial Autoencoder Network for Hyperspectral Unmixing

Cited by 49 publications

References 41 publications

End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing

End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing

Dance emotion recognition based on linear predictive Meir frequency cepstrum coefficient and bidirectional long short-term memory from robot environment

Hyperspectral Unmixing Using Transformer Network

Contact Info

Product

Resources

About