Distributed Semantic Segmentation With Improved Rate-Distortion Trade-Off

2026-08-26

AI Summary

本文提出两种新的源编码器，以极低比特率改善率失真性能，优化分布式语义分割任务。

Abstract

Distributed deep neural networks (DNNs) for dense perception tasks such as semantic segmentation execute an encoder DNN on edge devices, and a decoder DNN typically on a large-scale cloud platform with a particular constraint on transmission bitrate. Recent works employ source codecs to enable bitrate-efficient transmission between the edge device and the cloud. However, as these approaches are typically bound to a particular type of source codec and alternative network architectures are often not explored, this results in a suboptimal rate-distortion (RD) trade-off in the low-bitrate regime. In this work, we propose two novel source codecs that \textit{enable extremely low bitrates, while improving RD performance}. We demonstrate the effectiveness of our proposed source codecs by achieving state-of-the-art performance in distributed semantic segmentation at below 0.2 (0.03) bits per pixel, measured using the mean intersection-over-union metric on ADE20K (Cityscapes).

Problem

• Distributed Deep Neural Networks
• Semantic Segmentation
• Rate-Distortion Trade-Off
• Low Bitrate

Innovation

• source codecs
• rate-distortion trade-off
• distributed semantic segmentation