An Efficient Object Detection Algorithm Based on Compressed Networks
AbstractFor a long time, object detection has been a popular but difficult research problem in the field of pattern recognition. In recent years, object detection algorithms based on convolutional neural networks have achieved excellent results. However, neural networks are computationally intensive and parameter redundant, so they are difficult to deploy on resource-limited embedded devices. Especially for two-stage detectors, operations and parameters are mainly clustered on feature fusion of proposals after the region of interest (ROI) pooling layer, and they are enormous. In order to deal with these problems, we propose a subnetwork—efficient feature fusion module (EFFM) to reduce the number of operations and parameters for a two-stage detector. In addition, we propose a multi-scale dilation region proposal network (RPN) to further improve detection accuracy. Finally, our accuracy is higher than Faster RCNN based on VGG16, the number of operations is only half of the latter, and the number of parameters is only one third. View Full-Text
Share & Cite This Article
Li, J.; Peng, K.; Chang, C.-C. An Efficient Object Detection Algorithm Based on Compressed Networks. Symmetry 2018, 10, 235.
Li J, Peng K, Chang C-C. An Efficient Object Detection Algorithm Based on Compressed Networks. Symmetry. 2018; 10(7):235.Chicago/Turabian Style
Li, Jianjun; Peng, Kangjian; Chang, Chin-Chen. 2018. "An Efficient Object Detection Algorithm Based on Compressed Networks." Symmetry 10, no. 7: 235.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.