An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions
This work addresses the need for efficient semantic segmentation for applications like autonomous driving and robotics, though it is incremental as it builds on existing architectures.
The paper tackles the problem of computational efficiency in semantic segmentation by proposing a network based on ShuffleNet V2 with atrous separable convolutions, achieving a mean intersection over union (mIOU) of 70.33% on the Cityscapes challenge and enabling real-time performance on mobile devices.
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.