Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding
This work addresses scalability and computational efficiency for distributed AI services, particularly in edge-cloud setups, though it is incremental as it builds on existing distributed computing frameworks.
The paper tackled the problem of distributed semantic segmentation by proposing joint source and task decoding to reduce cloud network size, achieving state-of-the-art performance across bitrates while using only 9.8% to 11.59% of cloud DNN parameters compared to previous methods on COCO and Cityscapes datasets.
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.