RTSeg: Real-time Semantic Segmentation Comparative Study

TL;DR

This paper introduces a benchmarking framework for real-time semantic segmentation, enabling principled evaluation of different architectures and design choices to improve efficiency without sacrificing accuracy.

Contribution

It presents a modular, decoupled benchmarking framework for semantic segmentation that facilitates comparison and development of computationally efficient models.

Findings

Achieved up to 143x GFLOPs reduction compared to SegNet.

Provided a publicly available benchmarking platform.

Demonstrated the effectiveness of various architecture combinations.

Abstract

Semantic segmentation benefits robotics related applications especially autonomous driving. Most of the research on semantic segmentation is only on increasing the accuracy of segmentation models with little attention to computationally efficient solutions. The few work conducted in this direction does not provide principled methods to evaluate the different design choices for segmentation. In this paper, we address this gap by presenting a real-time semantic segmentation benchmarking framework with a decoupled design for feature extraction and decoding methods. The framework is comprised of different network architectures for feature extraction such as VGG16, Resnet18, MobileNet, and ShuffleNet. It is also comprised of multiple meta-architectures for segmentation that define the decoding methodology. These include SkipNet, UNet, and Dilation Frontend. Experimental results are presented on the Cityscapes dataset for urban scenes. The modular design allows novel architectures to emerge, that lead to 143x GFLOPs reduction in comparison to SegNet. This benchmarking framework is publicly available at "https://github.com/MSiam/TFSegmentation".