Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation
This work addresses the problem of adaptive deep learning deployment for mobile object detection, offering a novel configurable approach that is robust and incremental in improving efficiency.
The paper tackles the challenge of deploying object detection on mobile devices under fluctuating operational constraints like bandwidth and computation, by introducing a configurable solution that manages the communication-computation-accuracy trade-off with a single set of weights, achieving state-of-the-art results on COCO-2017 with only a minor penalty on the base architecture.
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.