提出新编码方法，在极低比特率下提升分割精度。
Distributed Semantic Segmentation With Improved Rate-Distortion Trade-Off
- 设计两种新型源编码器，优化边缘到云端的传输效率。
- 在低于0.2比特/像素时，达到ADE20K和Cityscapes上的最优分割性能。
- 适合资源受限设备进行高效语义分割部署。
面向语义分割等密集感知任务，分布式深度神经网络通常在边缘设备运行编码器，在大型云平台运行解码器，并受传输码率限制。现有方法使用特定源编码器实现低码率传输，但受限于固定编码方式且难以探索其他网络结构，导致低码率下率失真（RD）权衡不佳。本文提出两种新型源编码器，可实现极低码率并显著提升RD性能。实验表明，在低于0.2比特/像素条件下，于ADE20K和Cityscapes数据集上以均交并比（mIoU）为指标，达到当前最优性能。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。