Irregular Tensor Low-Rank Representation for Hyperspectral Image Representation
This addresses the challenge of irregular spatial distributions in hyperspectral image analysis, which is important for remote sensing applications, though it appears to be an incremental improvement over existing low-rank tensor methods.
The paper tackles the problem of spectral variations in hyperspectral images by proposing an irregular tensor low-rank representation model that efficiently models irregular 3D cubes, demonstrating superior performance on four public datasets compared to existing state-of-the-art methods.
Spectral variations pose a common challenge in analyzing hyperspectral images (HSI). To address this, low-rank tensor representation has emerged as a robust strategy, leveraging inherent correlations within HSI data. However, the spatial distribution of ground objects in HSIs is inherently irregular, existing naturally in tensor format, with numerous class-specific regions manifesting as irregular tensors. Current low-rank representation techniques are designed for regular tensor structures and overlook this fundamental irregularity in real-world HSIs, leading to performance limitations. To tackle this issue, we propose a novel model for irregular tensor low-rank representation tailored to efficiently model irregular 3D cubes. By incorporating a non-convex nuclear norm to promote low-rankness and integrating a global negative low-rank term to enhance the discriminative ability, our proposed model is formulated as a constrained optimization problem and solved using an alternating augmented Lagrangian method. Experimental validation conducted on four public datasets demonstrates the superior performance of our method compared to existing state-of-the-art approaches. The code is publicly available at https://github.com/hb-studying/ITLRR.