# Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation

Source: [Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation](<https://www.sota2.com/research/paper/68fa6a791e209131cea28648>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:26:28.956Z

Authors: Juliano S. Assine, J. C. S. Santos Filho, Eduardo Valle

Published: 2021-05-03T01:08:34.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2105.00591>)

[PDF](<https://arxiv.org/pdf/2105.00591.pdf>)