@inproceedings{jiang2021flexible,
author = {Jiang, Shiqi and Lin, Zhiqi and Li, Yuanchun and Shu, Yuanchao and Liu, Yunxin},
title = {Flexible High-resolution Object Detection on Edge Devices with Tunable Latency},
organization = {Microsoft},
booktitle = {The 27th Annual International Conference On Mobile Computing And Networking (MobiCom '21))},
year = {2021},
month = {October},
abstract = {Object detection is a fundamental building block of video analytics applications. While Neural Networks (NNs)-based object detection models have shown excellent accuracy on benchmark datasets, they are not well positioned for high-resolution images inference on resource-constrained edge devices. Common approaches, including down-sampling inputs and scaling up neural networks, fall short of adapting to video content changes and various latency requirements. This paper presents Remix, a flexible framework for high-resolution object detection on edge devices. Remix takes as input a latency budget, and come up with an image partition and model execution plan which runs off-the-shelf neural networks on non-uniformly partitioned image blocks. As a result, it maximizes the overall detection accuracy by allocating various amount of compute power onto different areas of an image. We evaluate Remix on public dataset as well as real-world videos collected by ourselves. Experimental results show that Remix can either improve the detection accuracy by 18%-70% for a given latency budget, or achieve up to 5.5x inference speedup with accuracy on par with the state-of-the-art NNs.},
publisher = {ACM},
url = {http://approjects.co.za/?big=en-us/research/publication/flexible-high-resolution-object-detection-on-edge-devices-with-tunable-latency/},
}