# Deep Joint Source-Channel Coding for Multi-Task Network

Source: [Deep Joint Source-Channel Coding for Multi-Task Network](<https://www.sota2.com/research/paper/68fa6b271e209131cea2c596>)

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

Data updated: 2025-10-25T23:41:15.837Z

Authors: Mengyang Wang, Zhicong Zhang, Jiahui Li, Mengyao Ma, Xiaopeng Fan

Published: 2021-09-13T08:58:02.000Z

## Abstract

Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by sharing knowledge. However, most existing MTL networks run on a single end and are not suitable for collaborative intelligence (CI) scenarios. In this work, we propose an MTL network with a deep joint source-channel coding (JSCC) framework, which allows operating under CI scenarios. We first propose a feature fusion based MTL network (FFMNet) for joint object detection and semantic segmentation. Compared with other MTL networks, FFMNet gets higher performance with fewer parameters. Then FFMNet is split into two parts, which run on a mobile device and an edge server respectively. The feature generated by the mobile device is transmitted through the wireless channel to the edge server. To reduce the transmission overhead of the intermediate feature, a deep JSCC network is designed. By combining two networks together, the whole model achieves 512x compression for the intermediate feature and a performance loss within 2% on both tasks. At last, by training with noise, the FFMNet with JSCC is robust to various channel conditions and outperforms the separate source and channel coding scheme.

## 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/2109.05779>)

[PDF](<https://arxiv.org/pdf/2109.05779.pdf>)
