# A Method for Few-Shot Radar Target Recognition Based on Multimodal Feature Fusion

## TL;DR

This paper presents a new few-shot learning method for radar target recognition that uses multimodal feature fusion to improve accuracy and reduce reliance on large datasets.

## Contribution

The novel contribution is a cross-modal fusion framework with an energy embedding strategy and a cross-modal equilibrium loss function for radar target recognition.

## Key findings

- The proposed method achieves 95.36% accuracy in a 5-way 1-shot task.
- It outperforms traditional methods by 2.26% and 8.73% in recognition accuracy.
- Inter-class feature separation is improved by 18.37%.

## Abstract

Enhancing generalization capabilities and robustness in scenarios with limited sample sizes, while simultaneously decreasing reliance on extensive and high-quality datasets, represents a significant area of inquiry within the domain of radar target recognition. This study introduces a few-shot learning framework that leverages multimodal feature fusion. We develop a cross-modal representation optimization mechanism tailored for the target recognition task by incorporating natural resonance frequency features that elucidate the target’s scattering characteristics. Furthermore, we establish a multimodal fusion classification network that integrates bi-directional long short-term memory and residual neural network architectures, facilitating deep bimodal fusion through an encoding-decoding framework augmented by an energy embedding strategy. To optimize the model, we propose a cross-modal equilibrium loss function that amalgamates similarity metrics from diverse features with cross-entropy loss, thereby guiding the optimization process towards enhancing metric spatial discrimination and balancing classification performance. Empirical results derived from simulated datasets indicate that the proposed methodology achieves a recognition accuracy of 95.36% in the 5-way 1-shot task, surpassing traditional unimodal image and concatenation fusion feature approaches by 2.26% and 8.73%, respectively. Additionally, the inter-class feature separation is improved by 18.37%, thereby substantiating the efficacy of the proposed method.