MFFA-SARNET: Deep Transferred Multi-Level Feature Fusion Attention Network with Dual Optimized Loss for Small-Sample SAR ATR
Open Access
- 27 April 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (9), 1385
- https://doi.org/10.3390/rs12091385
Abstract
Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR), most algorithms of which have employed and relied on sufficient training samples to receive a strong discriminative classification model, has remained a challenging task in recent years, among which the challenge of SAR data acquisition and further insight into the intuitive features of SAR images are the main concerns. In this paper, a deep transferred multi-level feature fusion attention network with dual optimized loss, called a multi-level feature attention Synthetic Aperture Radar network (MFFA-SARNET), is proposed to settle the problem of small samples in SAR ATR tasks. Firstly, a multi-level feature attention (MFFA) network is established to learn more discriminative features from SAR images with a fusion method, followed by alleviating the impact of background features on images with the following attention module that focuses more on the target features. Secondly, a novel dual optimized loss is incorporated to further optimize the classification network, which enhances the robust and discriminative learning power of features. Thirdly, transfer learning is utilized to validate the variances and small-sample classification tasks. Extensive experiments conducted on a public database with three different configurations consistently demonstrate the effectiveness of our proposed network, and the significant improvements yielded to surpass those of the state-of-the-art methods under small-sample conditions.Funding Information
- National Natural Science Foundation of China (61771347)
This publication has 45 references indexed in Scilit:
- Dual and Single Polarized SAR Image Classification Using Compact Convolutional Neural NetworksRemote Sensing, 2019
- Fast Semisupervised Classification Using Histogram-Based Density Estimation for Large-Scale Polarimetric SAR DataIEEE Geoscience and Remote Sensing Letters, 2019
- High-Performance SAR Image Matching Using Improved SIFT Framework Based on Rolling Guidance Filter and ROEWA-Powered FeatureIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
- A Novel Local Human Visual Perceptual Texture Description with Key Feature Selection for Texture ClassificationMathematical Problems in Engineering, 2019
- A Modified Local Binary Pattern Descriptor for SAR Image MatchingIEEE Geoscience and Remote Sensing Letters, 2018
- Automatic Target Recognition Within Anomalous Regions of Interest in Hyperspectral ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018
- SAR Automatic Target Recognition Using a Roto-Translational Invariant Wavelet-Scattering Convolution NetworkRemote Sensing, 2018
- SAR Automatic Target Recognition Based on Multiview Deep Learning FrameworkIEEE Transactions on Geoscience and Remote Sensing, 2017
- Remote Sensing Image Scene Classification: Benchmark and State of the ArtProceedings of the IEEE, 2017
- Convolutional Neural Network With Data Augmentation for SAR Target RecognitionIEEE Geoscience and Remote Sensing Letters, 2016