High-Precision Binary Object Detector Based on a BSF-XNOR Convolutional Layer

Abstract

Recently, building an efficient and robust model for object detection has attracted the attention of the vision community. Although binary networks have a fast inference speed, they cannot be used directly on mobile devices such as unmanned aerial vehicles (UAVs) because of their low detection accuracy. Dfferent from improving the detection accuracy of a binary network by adjusting the network structure or adjusting the update gradient, we propose an improved binary neural network based on the block scaling factor XNOR (BSF-XNOR) convolutional layer. In addition, we propose a two-level densely connected network structure, which further enhances the network layer's feature representation capabilities. Experiments using the TensorFlow framework prove the effectiveness of our algorithm in improving accuracy. Compared with the original standard XNOR network, the mean average precision (mAP) detected by our algorithm on the PASCAL VOC dataset was improved. The experimental results on the VisDrone2019 UAV dataset confirm that our method achieves a better balance between speed and accuracy than previous methods. Our algorithm aims to guide and deploy high-precision binary networks on the embedded device and solves the problem of low-precision binary networks.

A Systematic Literature Review on Binary Neural Networks

“…This algorithm reduced the angular and amplitude error learning by utilizing a differential binarization search and the scale factor. Also, S. WANG et al [251] introduced Block Scaling Factor XNOR (BSF-XNOR) convolutional layer and two-level densely connected network structure. While J. Zhao et al [247] presented DA-BNN, which used an adaptive amplitude mechanism to improve the feature representation.…”