Transductive Prototypical Attention Reasoning Network for Few-Shot SAR Target Recognition


METADATA ONLY
Loading...

Date

2023

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Deep-learning-based synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms have achieved outstanding performance under the condition of hundreds or thousands of training samples in recent years. Nevertheless, it is often rare to acquire great quantities of target samples in real SAR application scenarios. This article proposes a novel ATR method called transductive prototypical attention reasoning network (TPARN) to solve the problem of SAR target recognition with only a few training samples. To be specific, a region-awareness-based feature extraction model is first developed, which can effectively focus on the target region of interest (RoI) and suppress the background clutter by embedding direction-aware and position-sensitive information to extract more transferable knowledge. To heighten the discrimination of the sample features, a cross-feature spatial attention (CFSA) module is then proposed following the feature embedding model. Finally, a transductive prototype reasoning method is presented to realize the identity reasoning of the target, which can continuously update each class prototype with training samples and test samples together, thereby improving the classification accuracy. In addition, a marginal adaptive hybrid loss (MAHL) is proposed to obtain a discriminative feature embedding space with intraclass compactness and interclass divergence, aiming to facilitate subsequent target identity reasoning. Extensive experiments on the moving and stationary target acquisition and recognition (MSTAR) benchmark dataset reveal that the proposed method outperforms some state-of-the-arts under different few-shot SAR ATR tasks.

Publication status

published

Editor

Book title

Volume

61

Pages / Article No.

5206813

Publisher

IEEE

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Automatic target recognition (ATR); convolutional neural network (CNN); few-shot learning (FSL); synthetic aperture radar (SAR)

Organisational unit

Notes

Funding

Related publications and datasets