# An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions

## TL;DR

This paper introduces a computationally efficient semantic segmentation model based on ShuffleNet V2 with atrous separable convolutions, achieving high accuracy and real-time performance on mobile devices.

## Contribution

The paper presents a novel, efficient neural network architecture for semantic segmentation that balances accuracy and computational cost, suitable for mobile deployment.

## Key findings

- Achieved 70.33% mIOU on Cityscapes.
- Capable of real-time processing on mobile devices.
- Code and models are publicly available.

## Abstract

Assigning a label to each pixel in an image, namely semantic segmentation, has been an important task in computer vision, and has applications in autonomous driving, robotic navigation, localization, and scene understanding. Fully convolutional neural networks have proved to be a successful solution for the task over the years but most of the work being done focuses primarily on accuracy. In this paper, we present a computationally efficient approach to semantic segmentation, while achieving a high mean intersection over union (mIOU), 70.33% on Cityscapes challenge. The network proposed is capable of running real-time on mobile devices. In addition, we make our code and model weights publicly available.