Share Email Print
cover

Proceedings Paper • new

Tiny-RetinaNet: a one-stage detector for real-time object detection
Author(s): Miao Cheng; Jianan Bai; Luyi Li; Qing Chen; Xiangming Zhou; Hequn Zhang; Peng Zhang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we present a new one stage detector for object detection. In order to meet the requirements of real-time detection, we use MobileNetV2-FPN as backbone for feature extraction. The lightweight depthwise separable convolutions can improve the speed of detection and make the model smaller. In order to improve the accuracy of our small detection model, we add Stem Block into backbone and we add SEnet in front of two task-specific subnets. The stem block can reduce the information loss from raw input images. The SEnet can enhance useful features from backbone network and suppress features that are little use to two-specific tasks. Inspired by RetinaNet, we also use Focal Loss as our classification loss function. We measure our performance on PASCAL VOC2007 and PASCAL VOC2012. Our detector with 300300 input achieves 73.8% mAP on VOC2007 test, 71.4% mAP on VOC2012 test. And our detector can run at 97FPS and the number of parameters is only 7.7M that meets the requirements of real-time detection. The accuracy of our detector is close to SSD, our detector uses about only 1/3 parameters to SSD. Keywords: One-

Paper Details

Date Published: 3 January 2020
PDF: 8 pages
Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 113730R (3 January 2020); doi: 10.1117/12.2557264
Show Author Affiliations
Miao Cheng, Zhejiang Dahua Technology Co., Ltd. (China)
Jianan Bai, Zhejiang Dahua Technology Co., Ltd. (China)
Luyi Li, Zhejiang Dahua Technology Co., Ltd. (China)
Qing Chen, Zhejiang Dahua Technology Co., Ltd. (China)
Xiangming Zhou, Zhejiang Dahua Technology Co., Ltd. (China)
Hequn Zhang, Zhejiang Dahua Technology Co., Ltd. (China)
Peng Zhang, Zhejiang Dahua Technology Co., Ltd. (China)


Published in SPIE Proceedings Vol. 11373:
Eleventh International Conference on Graphics and Image Processing (ICGIP 2019)
Zhigeng Pan; Xun Wang, Editor(s)

© SPIE. Terms of Use
Back to Top