Design of Real-time Semantic Segmentation Decoder for Automated Driving
This work addresses the real-time performance bottleneck in automated driving systems, though it is incremental as it builds on existing encoder designs.
The paper tackles the computational inefficiency of semantic segmentation decoders for automated driving by designing a novel efficient non-bottleneck layer and a family of decoders, achieving a 10% improvement over a baseline performance.
Semantic segmentation remains a computationally intensive algorithm for embedded deployment even with the rapid growth of computation power. Thus efficient network design is a critical aspect especially for applications like automated driving which requires real-time performance. Recently, there has been a lot of research on designing efficient encoders that are mostly task agnostic. Unlike image classification and bounding box object detection tasks, decoders are computationally expensive as well for semantic segmentation task. In this work, we focus on efficient design of the segmentation decoder and assume that an efficient encoder is already designed to provide shared features for a multi-task learning system. We design a novel efficient non-bottleneck layer and a family of decoders which fit into a small run-time budget using VGG10 as efficient encoder. We demonstrate in our dataset that experimentation with various design choices led to an improvement of 10\% from a baseline performance.