Journal
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
Volume 19, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2020.3037256
Keywords
Radar polarimetry; Convolution; Synthetic aperture radar; Target recognition; Kernel; Training; Image recognition; Automatic target recognition; channel attention; convolutional neural network (CNN); spatial attention; synthetic aperture radar (SAR)
Categories
Funding
- National Natural Science Foundation of China [61806219, 61876189, 61503407, 61703426, 61273275]
- Young Talent fund of University Association for Science and Technology in Shaanxi, China [20190108]
Ask authors/readers for more resources
This letter proposes a fully convolutional attention block (FCAB) that can be combined with a CNN to refine important features and suppress unnecessary ones in synthetic aperture radar (SAR) images. Experimental results demonstrate that FCAB can focus on important channels and object regions, while being computationally efficient and bringing about significant performance gain for SAR recognition.
Attention mechanisms have recently shown strong potential in improving the performance of convolutional neural networks (CNNs). This letter proposes a fully convolutional attention block (FCAB) that can be combined with a CNN to refine important features and suppress unnecessary ones in synthetic aperture radar (SAR) images. The FCAB consists of a channel attention module and a spatial attention module. For the channel attention module, we use average-pooling and max-pooling to learn complementary features, and apply group convolution to aggregate the information of the two types of channels. Global average-pooling is then used to encode the channel-wise importance. For the spatial attention module, the average-pooling and max-pooling along the channel axis are used to generate two spatial feature maps, and then two very lightweight convolutional layers are used to encode the spatial weight map. Experimental results on SAR images demonstrate that our FCAB can focus on important channels and object regions. It uses relatively few parameters and is computationally efficient, while bringing about significant performance gain for SAR recognition.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available