Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration

Kang, Jian; Hong, Danfeng; Liu, Jialin; Baier, Gerald; Yokoya, Naoto; Demir, Begüm

doi:10.1109/tnnls.2020.2979546

Cited by 61 publications

(22 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The iterative alternating strategy used in Algorithm 1 is nothing but a block coordinate descent, whose convergence is theoretically guaranteed as long as each subproblem of (12) is exactly minimized [47]. Each subproblem optimized in Algorithm 2 is strongly convex, and thus the ADMM-based optimization strategy can converge to a unique minimum when the parameters are updated in finite steps [48], [49]. Moreover, we experimentally illustrate to clarify the convergences of J-Play and the proposed JPSA on the two HS datasets, where the relative errors of the objective function value are recorded in each iteration (see Fig.…”

Section: Convergence Analysismentioning

confidence: 99%

Joint and Progressive Subspace Analysis (JPSA) With Spatial–Spectral Manifold Alignment for Semisupervised Hyperspectral Dimensionality Reduction

Hong

Yokoya

Chanussot

et al. 2021

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

This is the pre-acceptance version, to read the final version please go to IEEE Transactions on Cybernetics on IEEE Xplore. Conventional nonlinear subspace learning techniques (e.g., manifold learning) usually introduce some drawbacks in explainability (explicit mapping) and cost-effectiveness (linearization), generalization capability (out-of-sample), and representability (spatial-spectral discrimination). To overcome these shortcomings, a novel linearized subspace analysis technique with spatial-spectral manifold alignment is developed for a semi-supervised hyperspectral dimensionality reduction (HDR), called joint and progressive subspace analysis (JPSA). The JPSA learns a high-level, semantically meaningful, joint spatialspectral feature representation from hyperspectral data by 1) jointly learning latent subspaces and a linear classifier to find an effective projection direction favorable for classification; 2) progressively searching several intermediate states of subspaces to approach an optimal mapping from the original space to a This paper is an extended version in algorithm of [1] published in ECCV2018.

show abstract

Section: Convergence Analysismentioning

confidence: 99%

Joint and Progressive Subspace Analysis (JPSA) With Spatial–Spectral Manifold Alignment for Semisupervised Hyperspectral Dimensionality Reduction

Hong

Yokoya

Chanussot

et al. 2021

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Early attempts exploiting HSI mostly employed support vector machines (SVM) [11][12][13], K-means clustering (KNN) [14], and polynomial logistic regression (MLR) [15] schemes. Traditional feature extraction mostly relies on feature extractors designed by human experts [16,17] exploiting the domain knowledge and engineering experience. However, these feature extractors are not appealing in the HSI classification domain as they ignore the spatial correlation and local consistency and neglect exploiting the spatial feature information of HSI.…”

Section: Introductionmentioning

confidence: 99%

Improved Transformer Net for Hyperspectral Image Classification

et al. 2021

View full text Add to dashboard Cite

In recent years, deep learning has been successfully applied to hyperspectral image classification (HSI) problems, with several convolutional neural network (CNN) based models achieving an appealing classification performance. However, due to the multi-band nature and the data redundancy of the hyperspectral data, the CNN model underperforms in such a continuous data domain. Thus, in this article, we propose an end-to-end transformer model entitled SAT Net that is appropriate for HSI classification and relies on the self-attention mechanism. The proposed model uses the spectral attention mechanism and the self-attention mechanism to extract the spectral–spatial features of the HSI image, respectively. Initially, the original HSI data are remapped into multiple vectors containing a series of planar 2D patches after passing through the spectral attention module. On each vector, we perform linear transformation compression to obtain the sequence vector length. During this process, we add the position–coding vector and the learnable–embedding vector to manage capturing the continuous spectrum relationship in the HSI at a long distance. Then, we employ several multiple multi-head self-attention modules to extract the image features and complete the proposed network with a residual network structure to solve the gradient dispersion and over-fitting problems. Finally, we employ a multilayer perceptron for the HSI classification. We evaluate SAT Net on three publicly available hyperspectral datasets and challenge our classification performance against five current classification methods employing several metrics, i.e., overall and average classification accuracy and Kappa coefficient. Our trials demonstrate that SAT Net attains a competitive classification highlighting that a Self-Attention Transformer network and is appealing for HSI classification.

show abstract

“…To address the challenge, we employed the transfer sparse coding (TSC) approach [12] [13], which has successfully extended the applications of the sparse coding [14][15][16][17] in the two domains. We extended TSC to adapt the three domains transfer learning problem based on the following key ideas.…”

Section: Introductionmentioning

confidence: 99%

Transitive Transfer Sparse Coding for Distant Domain

Feng

Qian

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The transfer learning between the source and target domain has already achieved significant success in machine learning areas. However, the existing methods can not achieve satisfactory result when solving the two distant domains transfer learning problem. In the worst case, it could lead to the negative transfer. In this paper, we propose a novel framework called transitive transfer sparse coding (TTSC) to solve the two distant domains transfer learning problem. On the one hand, as an extension of the sparse coding, the TTSC framework constructs a robust and high-level dictionary across three different domains and simultaneously obtains three good feature sparse representations. On the other hand, TTSC utilizes the intermediate domain as a strong bridge to transfer valuable knowledge between the source domain and target domain. Empirical studies validated that the TTSC framework significantly could outperform state-of-the-art methods.

show abstract

Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration

Cited by 61 publications

References 59 publications

Joint and Progressive Subspace Analysis (JPSA) With Spatial–Spectral Manifold Alignment for Semisupervised Hyperspectral Dimensionality Reduction

Joint and Progressive Subspace Analysis (JPSA) With Spatial–Spectral Manifold Alignment for Semisupervised Hyperspectral Dimensionality Reduction

Improved Transformer Net for Hyperspectral Image Classification

Transitive Transfer Sparse Coding for Distant Domain

Contact Info

Product

Resources

About