Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding

TL;DR

This paper introduces a joint source and task decoding approach for distributed semantic segmentation, reducing cloud network size and computational load while achieving state-of-the-art performance across various bitrates.

Contribution

It proposes a novel joint decoding method that decreases cloud network size and enhances scalability in distributed semantic segmentation tasks.

Findings

Achieves state-of-the-art segmentation performance over various bitrates.

Uses only 9.8% to 11.59% of cloud DNN parameters compared to previous SOTA.

Demonstrates scalability and efficiency in large-scale distributed systems.

Abstract

Distributed computing in the context of deep neural networks (DNNs) implies the execution of one part of the network on edge devices and the other part typically on a large-scale cloud platform. Conventional methods propose to employ a serial concatenation of a learned image and source encoder, the latter projecting the image encoder output (bottleneck features) into a quantized representation for bitrate-efficient transmission. In the cloud, a respective source decoder reprojects the quantized representation to the original feature representation, serving as an input for the downstream task decoder performing, e.g., semantic segmentation. In this work, we propose joint source and task decoding, as it allows for a smaller network size in the cloud. This further enables the scalability of such services in large numbers without requiring extensive computational load on the cloud per channel. We demonstrate the effectiveness of our method by achieving a distributed semantic segmentation SOTA over a wide range of bitrates on the mean intersection over union metric, while using only $9.8 \%$ ... $11.59 \%$ of cloud DNN parameters used in the previous SOTA on the COCO and Cityscapes datasets.