Tensor Alignment Based Domain Adaptation for Hyperspectral Image Classification

TL;DR

This paper introduces a tensor alignment domain adaptation method for hyperspectral image classification that leverages superpixel segmentation, Tucker decomposition, and manifold regularization to improve accuracy with limited labeled data.

Contribution

The novel approach combines tensor alignment with manifold regularization and superpixel segmentation for improved hyperspectral image classification in domain adaptation.

Findings

Outperforms state-of-the-art subspace learning methods.

Effective with limited labeled source samples.

Achieves higher classification accuracy on real HSIs.

Abstract

This paper presents a tensor alignment (TA) based domain adaptation method for hyperspectral image (HSI) classification. To be specific, HSIs in both domains are first segmented into superpixels and tensors of both domains are constructed to include neighboring samples from single superpixel. Then we consider the subspace invariance between two domains as projection matrices and original tensors are projected as core tensors with lower dimensions into the invariant tensor subspace by applying Tucker decomposition. To preserve geometric information in original tensors, we employ a manifold regularization term for core tensors into the decomposition progress. The projection matrices and core tensors are solved in an alternating optimization manner and the convergence of TA algorithm is analyzed. In addition, a post-processing strategy is defined via pure samples extraction for each superpixel to further improve classification performance. Experimental results on four real HSIs demonstrate that the proposed method can achieve better performance compared with the state-of-the-art subspace learning methods when a limited amount of source labeled samples are available.