An Information-Reserved and Deviation-Controllable Binary Neural Network for Object Detection

Ganlin Zhu, Hongxiao Fei, Junkun Hong, Yueyi Luo and Jun Long ()
Additional contact information
Ganlin Zhu: School of Computer Science and Engineering, Central South University, Changsha 410018, China
Hongxiao Fei: School of Computer Science and Engineering, Central South University, Changsha 410018, China
Junkun Hong: School of Computer Science and Engineering, Central South University, Changsha 410018, China
Yueyi Luo: School of Computer Science and Engineering, Central South University, Changsha 410018, China
Jun Long: Institute of Big Data, Central South University, Changsha 410018, China

Mathematics, 2022, vol. 11, issue 1, 1-18

Abstract: Object detection is a fundamental task in computer vision, which is usually based on convolutional neural networks (CNNs). While it is difficult to be deployed in embedded devices due to the huge storage and computing consumptions, binary neural networks (BNNs) can execute object detection with limited resources. However, the extreme quantification in BNN causes diversity of feature representation loss, which eventually influences the object detection performance. In this paper, we propose a method balancing I nformation R etention and D eviation C ontrol to achieve effective object detection, named IR-DC Net. On the one hand, we introduce the KL-Divergence to compose multiple entropy for maximizing the available information. On the other hand, we design a lightweight convolutional module to generate scale factors dynamically for minimizing the deviation between binary and real convolution. The experiments on PASCAL VOC, COCO2014, KITTI, and VisDrone datasets show that our method improved the accuracy in comparison with previous binary neural networks.

Keywords: object detection; binary convolutional neural network; information entropy; loss function; scale factor (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/1/62/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/1/62/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2022:i:1:p:62-:d:1013684

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().