# Dual-Branch Residual Network for Cross-Domain Few-Shot Hyperspectral Image Classification with Refined Prototype

arXiv: https://arxiv.org/abs/2504.19074 · HTML: https://mlsanity.com/paper/2504.19074/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 12 references that are in the map.
- First posted on arXiv 27 Apr 2025.

## Builds on (most cited first, 1 of 1)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)

## Abstract (arXiv)

Convolutional neural networks (CNNs) are effective for hyperspectral image (HSI) classification, but their 3D convolutional structures introduce high computational costs and limited generalization in few-shot scenarios. Domain shifts caused by sensor differences and environmental variations further hinder cross-dataset adaptability. Metric-based few-shot learning (FSL) prototype networks mitigate this problem, yet their performance is sensitive to prototype quality, especially with limited samples. To overcome these challenges, a dual-branch residual network that integrates spatial and spectral features via parallel branches is proposed in this letter. Additionally, more robust refined prototypes are obtained through a regulation term. Furthermore, a kernel probability matching strategy aligns source and target domain features, alleviating domain shift. Experiments on four publicly available HSI datasets illustrate that the proposal achieves superior performance compared to other methods.