Multi-Scale U-Shape MLP for Hyperspectral Image Classification

TL;DR

This paper introduces MUMLP, a novel multi-scale U-shape MLP model that effectively captures local and global spectral information in hyperspectral images while reducing model complexity, outperforming existing methods on multiple datasets.

Contribution

The paper proposes a new Multi-Scale U-shape MLP architecture with MSC and UMLP components, improving spectral feature representation and parameter efficiency for hyperspectral image classification.

Findings

Outperforms state-of-the-art methods on three public datasets.

Effectively captures local and global spectral information.

Reduces model parameters while maintaining high accuracy.

Abstract

Hyperspectral images have significant applications in various domains, since they register numerous semantic and spatial information in the spectral band with spatial variability of spectral signatures. Two critical challenges in identifying pixels of the hyperspectral image are respectively representing the correlated information among the local and global, as well as the abundant parameters of the model. To tackle this challenge, we propose a Multi-Scale U-shape Multi-Layer Perceptron (MUMLP) a model consisting of the designed MSC (Multi-Scale Channel) block and the UMLP (U-shape Multi-Layer Perceptron) structure. MSC transforms the channel dimension and mixes spectral band feature to embed the deep-level representation adequately. UMLP is designed by the encoder-decoder structure with multi-layer perceptron layers, which is capable of compressing the large-scale parameters. Extensive experiments are conducted to demonstrate our model can outperform state-of-the-art methods across-the-board on three wide-adopted public datasets, namely Pavia University, Houston 2013 and Houston 2018