# A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification

## TL;DR

This paper introduces A2S-NAS, a neural architecture search method that adaptively captures spectral-spatial features in hyperspectral images by addressing fixed receptive fields and asymmetry, leading to improved classification accuracy.

## Contribution

The paper proposes a multi-stage NAS framework that incorporates asymmetric spectral-spatial pooling and flexible 3D convolutions to better handle hyperspectral image features.

## Key findings

- Achieves superior classification performance on Indian Pines and Houston datasets.
- Effectively captures spectral-spatial features with adaptive receptive fields.
- Outperforms existing methods in hyperspectral image classification.

## Abstract

Existing deep learning-based hyperspectral image (HSI) classification works still suffer from the limitation of the fixed-sized receptive field, leading to difficulties in distinctive spectral-spatial features for ground objects with various sizes and arbitrary shapes. Meanwhile, plenty of previous works ignore asymmetric spectral-spatial dimensions in HSI. To address the above issues, we propose a multi-stage search architecture in order to overcome asymmetric spectral-spatial dimensions and capture significant features. First, the asymmetric pooling on the spectral-spatial dimension maximally retains the essential features of HSI. Then, the 3D convolution with a selectable range of receptive fields overcomes the constraints of fixed-sized convolution kernels. Finally, we extend these two searchable operations to different layers of each stage to build the final architecture. Extensive experiments are conducted on two challenging HSI benchmarks including Indian Pines and Houston University, and results demonstrate the effectiveness of the proposed method with superior performance compared with the related works.