# Multi-Center Prototype Feature Distribution Reconstruction for Class-Incremental SAR Target Recognition

## TL;DR

This paper introduces a new method for improving SAR target recognition systems that can learn new targets without forgetting old ones.

## Contribution

The novel MPFR method uses multi-center prototypes and a hybrid attention feature extractor to reduce forgetting in class-incremental learning for SAR ATR.

## Key findings

- MPFR outperforms existing methods on public SAR datasets in class-incremental learning tasks.
- The multi-scale hybrid attention extractor effectively captures discriminative features from SAR data.
- Ablation studies confirm the importance of each component in the proposed method.

## Abstract

In practical applications of deep learning-based Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems, new target categories emerge continuously. This requires the systems to learn incrementally—acquiring new knowledge while retaining previously learned information. To mitigate catastrophic forgetting in Class-Incremental Learning (CIL), this paper proposes a CIL method for SAR ATR named Multi-center Prototype Feature Distribution Reconstruction (MPFR). It has two core components. First, a Multi-scale Hybrid Attention feature extractor is designed. Trained via a feature space optimization strategy, it fuses and extracts discriminative features from both SAR amplitude images and Attribute Scattering Center data, while preserving feature space capacity for new classes. Second, each class is represented by multiple prototypes to capture complex feature distributions. Old class knowledge is retained by modeling their feature distributions through parameterized Gaussian diffusion, alleviating feature confusion in incremental phases. Experiments on public SAR datasets show MPFR achieves superior performance compared to existing approaches, including recent SAR-specific CIL methods. Ablation studies validate each component’s contribution, confirming MPFR’s effectiveness in addressing CIL for SAR ATR without storing historical raw data.