Abstract
Although unsupervised representation learning (RL) can tackle the performance deterioration caused by limited labeled data in synthetic aperture radar (SAR) object classification, the neglected discriminative detailed information and the ignored distinctive characteristics of SAR images can lead to performance degradation. In this paper, an unsupervised multi-scale convolution auto-encoder (MSCAE) was proposed which can simultaneously obtain the global features and local characteristics of targets with its U-shaped architecture and pyramid pooling modules (PPMs). The compact depth-wise separable convolution and the deconvolution counterpart were devised to decrease the trainable parameters. The PPM and the multi-scale feature learning scheme were designed to learn multi-scale features. Prior knowledge of SAR speckle was also embedded in the model. The reconstruction loss of the MSCAE was measured by the structural similarity index metric (SSIM) of the reconstructed data and the images filtered by the improved Lee sigma filter. A speckle suppression restriction was also added in the objective function to guarantee that the speckle suppression procedure would take place in the feature learning stage. Experimental results with the MSTAR dataset under the standard operating condition and several extended operating conditions demonstrated the effectiveness of the proposed model in SAR object classification tasks.
Highlights
As the vital task of object classification with synthetic aperture radar (SAR) images, feature engineering intends to obtain robust representations of intrinsic properties to distinguish various targets in high-resolution radar images
The following compact depth-wise separable convolution (CSeConv) layers in each branch is employed to compress the process followed by a 3 × 3 CSeDeConv layer, a batch normalization (BN) operator and a ReLU activation function is applied pooled multi-channel feature map into a single-channel feature map, i.e., the sizes of the output to obtain the feature map of a coarser level that is the same size as the featureWmap at
In order to ensure comprehensive access to the performance, the proposed multi-scale convolution auto-encoder (MSCAE) was tested under standard operating condition (SOC) and various extended operating conditions (EOCs) including substantial variations in the signal-to-noise ratio (SNR), resolution, and version
Summary
As the vital task of object classification with synthetic aperture radar (SAR) images, feature engineering intends to obtain robust representations of intrinsic properties to distinguish various targets in high-resolution radar images. In Reference [34], Li et al proposed a stacked fisher AE for change detection, where the ratio difference image (RDI) of multi-temporal SAR images was used as the input and the distribution of the RDI was introduced to construct the objective function with sparsity regularization These AE-based models have developed an effective way to learn the robust representation via an unlabeled SAR dataset and achieved competitive results, the performance of most of these models is still slightly inferior to their supervised counterparts [35,36,37,38,39] and some handcrafted features [4,5,7] that are based on the electromagnetic scattering models.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
