SBNN: A Searched Binary Neural Network for SAR Ship Classification
Open Access
- 7 July 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 12 (14) , 6866
Abstract
The synthetic aperture radar (SAR) for ocean surveillance missions requires low latency and light weight inference. This paper proposes a novel small-size Searched Binary Network (SBNN), with network architecture search (NAS) for ship classification with SAR. In SBNN, convolution operations are modified by binarization technologies. Both input feature maps and weights are quantized into 1-bit in most of the convolution computation, which significantly decreases the overall computational complexity. In addition, we propose a patch shift processing, which can adjust feature maps with learnable parameters at spatial level. This process enhances the performance by reducing the information irrelevant to the targets. Experimental results on the OpenSARShip dataset show the proposed SBNN outperforms both binary neural networks from computer vision and CNN-based SAR ship classification methods. In particular, SBNN shows a great advantage in computational complexity.Keywords
Funding Information
- National Natural Science Foundation of China (62001227)
This publication has 28 references indexed in Scilit:
- OpenSARShip: A Dataset Dedicated to Sentinel-1 Ship InterpretationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016
- Merchant Vessel Classification Based on Scattering Component Analysis for COSMO-SkyMed SAR ImagesIEEE Geoscience and Remote Sensing Letters, 2013
- Ship Surveillance With TerraSAR-XIEEE Transactions on Geoscience and Remote Sensing, 2010
- The random subspace method for constructing decision forestsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Support-vector networksMachine Learning, 1995
- Synthetic aperture radar imaging of sea surface life and fishing activitiesIEEE Transactions on Geoscience and Remote Sensing, 1992
- Induction of decision treesMachine Learning, 1986