Deep Joint Source-Channel Coding for Multi-Task Network
This work addresses the challenge of efficient multi-task learning in collaborative intelligence settings, though it appears incremental as it builds on existing MTL and JSCC methods.
The authors tackled the problem of adapting multi-task learning networks for collaborative intelligence scenarios by proposing a deep joint source-channel coding framework that splits the network between a mobile device and an edge server, achieving 512x compression of intermediate features with less than 2% performance loss on object detection and semantic segmentation tasks.
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.