Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation
arXiv:2105.00591
Abstract
In the past few years, mobile deep-learning deployment progressed by leaps and bounds, but solutions still struggle to accommodate its severe and fluctuating operational restrictions, which include bandwidth, latency, computation, and energy. In this work, we help to bridge that gap, introducing the first configurable solution for object detection that manages the triple communication-computation-accuracy trade-off with a single set of weights. Our solution shows state-of-the-art results on COCO-2017, adding only a minor penalty on the base EfficientDet-D2 architecture. Our design is robust to the choice of base architecture and compressor and should adapt well for future architectures.
References in corpus (7)
- Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
- End-to-end Optimized Image Compression
- Joint Device-Edge Inference over Wireless Links with Pruning
- Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
- Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
- Split Computing for Complex Object Detectors: Challenges and Preliminary Results
- Compressing Representations for Embedded Deep Learning