Litcius/Paper detail

Multiarea Target Attention for Hyperspectral Image Classification

Huan Liu, Wei Li, Xiang‐Gen Xia, Mengmeng Zhang, Ran Tao

2023IEEE Transactions on Geoscience and Remote Sensing34 citationsDOI

Abstract

In hyperspectral image (HSI) classification, objects corresponding to pixels of different classes exhibit varying size characteristics, which causes a challenge for effective pixelwise feature extraction and classification. In this article, we propose a novel multiscale model, called multiarea target attention (MATA). The proposed MATA uses an architecture that includes a shared feature extractor (FE) and classifier to capture multiscale spectral–spatial information effectively and efficiently. The FE uses a multiscale target attention module (MSTAM) to extract spectral–spatial information from target pixels and their similar pixels across multiscale areas, while <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{2}$ </tex-math></inline-formula>-normalization is used to address discrepancies between features of different scales. The classifier adopts a classwise decision weighting strategy to account for the varying sizes of different classes and the different contributions of semantic features at each scale to each class. Experimental results on five public HSI datasets demonstrate that the proposed MATA outperforms existing state-of-the-art single- and multiscale models, confirming its effectiveness and efficiency in HSI classification. Code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/huanliu233/MATA</uri>.

Topics & Concepts

Hyperspectral imagingRemote sensingArtificial intelligenceComputer scienceContextual image classificationComputer visionImage (mathematics)Pattern recognition (psychology)Environmental scienceGeologyRemote-Sensing Image ClassificationRemote Sensing and Land UseAdvanced Image Fusion Techniques
Multiarea Target Attention for Hyperspectral Image Classification | Litcius