Few-Shot SAR ATR via Multilevel Contrastive Learning and Dependence Matrix-Based Measurement
In recent years, deep learning has achieved remarkable success in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of most deep learning-based models heavily depends on a large quantity of high-quality labeled data, which presents severe challenges in the c...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10919038/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In recent years, deep learning has achieved remarkable success in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of most deep learning-based models heavily depends on a large quantity of high-quality labeled data, which presents severe challenges in the collection and annotation of SAR images. To improve the stability and accuracy of few-shot SAR ATR, we propose a multilevel contrastive learning (MCL) driven and dependence matrix measured method, termed MCL-DMM. This method comprises two key components: the MCL module and the dependence matrix-based measurement (DMM) module. The MCL module enhances model performance by integrating both individual and cluster discriminative tasks, thereby leading to a plausible and powerful representation learning at both the individual and cluster level. This module aims to construct a robust and unbiased feature extractor with good intraclass tightness and interclass separateness. Building on this foundation, the DMM module models the dependencies within the feature matrix, providing a comprehensive measurement for few-shot SAR ATR. The cooperation between the robust feature extractor and the precise classifier enables the model to achieve superior performance. Experimental results on the standard MSATR dataset demonstrate that MCL-DMM outperforms current models, positioning it as a highly efficient solution for few-shot SAR ATR. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |