发表机构
Volkswagen AG; Institute for Communications Technology TU Braunschweig（大众汽车集团; 布伦瑞克工业大学通信技术研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对分布式语义分割低比特率下率失真权衡不佳的问题，提出两种新型信源码编解码器，在ADE20K、Cityscapes数据集上实现最优性能。
AI 中文摘要
用于语义分割等密集感知任务的分布式深度神经网络（DNN）会在边缘设备上执行编码器DNN，而解码器DNN通常运行在大规模云平台上，且对传输比特率有特定约束。现有研究采用信源码编解码器实现边缘设备与云之间的高效比特率传输，但这些方法通常绑定特定类型的信源码编解码器，且常未探索替代网络架构，导致低比特率场景下的率失真（RD）权衡未达最优。本研究提出两种新型信源码编解码器，可实现极低比特率同时提升RD性能。我们在低于0.2（0.03）比特每像素的条件下，于ADE20K（Cityscapes）数据集上采用平均交并比度量，取得分布式语义分割的最优性能，验证了所提信源码编解码器的有效性。
英文摘要
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).
Commentsaccepted at BMVC 2026 (Oral)
