Title | Light-Weight RetinaNet for Object Detection on Edge Devices |
Publication Type | Conference Proceedings |
Year of Publication | 2020 |
Authors | Li, YI, Dua, A, Ren, F |
Conference Name | The 2020 IEEE World Forum on Internet of Things (WF-IoT'20) |
Date Published | 04/2020 |
Conference Location | New Orleans, Louisiana |
Keywords (or New Research Field) | psclab |
Abstract | This paper aims at reducing computation for Retinanet, an mAP-30-tier network, to facilitate its practical deployment on edge devices for providing IoT-based object detection services. We first validate RetinaNet has the best FLOP-mAP trade-off among all mAP-30-tier network. Then, we propose a light-weight RetinaNet structure with effective computation-accuracy trade-off by only reducing FLOPs in computationally intensive layers. Compared with the most common way of trading off computation with accuracy-input image scaling, the proposed solution shows a consistently better FLOPs-mAP trade-off curve. Light-weight RetinaNet achieves a 0.3% mAP improvement at 1.Sx FLOPs reduction point over the original RetinaNet, and gains 1.Sx more energy-efficiency on an Intel Arria 10 FPGA accelerator in the context of edge computing. The proposed method potentially can help a wide range of the object detection applications to move closer to a preferred corner for a better runtime and accuracy, while enjoys more energy-efficient inference at the edge. |
Sign In / Sign Out
Navigation for Entire University