MixerCA: An Efficient and Accurate Model for High-Performance Hyperspectral Image Classification

TL;DR

MixerCA is a lightweight deep learning model that combines depthwise convolution and self-attention for efficient hyperspectral image classification, outperforming several existing methods.

Contribution

The paper introduces MixerCA, a novel model integrating depthwise convolutions and coordinate attention for improved HSI classification accuracy and efficiency.

Findings

MixerCA outperforms 2D-CNN, 3D-CNN, Tri-CNN, HybridSN, ViT, and Swin Transformer on benchmark datasets.

MixerCA maintains consistent resolution and decouples spatial and spectral features effectively.

The source code is publicly available at https://github.com/mqalkhatib/MixerCA.

Abstract

Over the past decade, hyperspectral image (HSI) classification has drawn considerable interest due to HSIs' ability to effectively distinguish terrestrial objects by capturing detailed, continuous spectral information. The strong performance of recent deep learning techniques in tasks like image classification and semantic segmentation has led to their growing use in HSI classification, due to their ability to capture complex spatial and spectral features more effectively than traditional methods. This paper presents MixerCA, a novel lightweight model for HSI classification that leverages depthwise convolution and a self-attention mechanism. MixerCA integrates depth-wise convolutions, token and channel mixing, and coordinate attention into a unified structure to decouple spatial and channel interactions, maintain consistent resolution throughout the network, and directly process HSI patches. Extensive experiments on four hyperspectral benchmark datasets reveal MixerCA's clear advantages over several competing algorithms, including 2D-CNN, 3D-CNN, Tri-CNN, HybridSN, ViT, and Swin Transformer. The source code is publicly available at https://github.com/mqalkhatib/MixerCA.