Towards High Performance Video Object Detection for Mobiles

Despite the recent success of video object detection on Desktop GPUs, its architecture is still far too heavy for mobiles. It is also unclear whether the key principles of sparse feature propagation and multi-frame feature aggregation apply at very limited computational resources. In this paper, we...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Zhu, Xizhou, Dai, Jifeng, Zhu, Xingchi, Wei, Yichen, Lu, Yuan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 16.04.2018
Subjects
Frames
Image detection
Object recognition
Product development
Propagation
Weight reduction
Online AccessGet full text

Cover

More Information
Summary:Despite the recent success of video object detection on Desktop GPUs, its architecture is still far too heavy for mobiles. It is also unclear whether the key principles of sparse feature propagation and multi-frame feature aggregation apply at very limited computational resources. In this paper, we present a light weight network architecture for video object detection on mobiles. Light weight image object detector is applied on sparse key frames. A very small network, Light Flow, is designed for establishing correspondence across frames. A flow-guided GRU module is designed to effectively aggregate features on key frames. For non-key frames, sparse feature propagation is performed. The whole network can be trained end-to-end. The proposed system achieves 60.2% mAP score at speed of 25.6 fps on mobiles (e.g., HuaWei Mate 8).
ISSN:2331-8422