Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars

TL;DR

This paper introduces a multi-scale spatial attention neural network for semantic segmentation in self-driving cars, achieving high accuracy and real-time performance on standard datasets.

Contribution

It proposes a novel attention module and multi-scale feature fusion approach that improves contextual understanding and efficiency in semantic segmentation networks.

Findings

Achieved a mean IOU of 74.12 on Cityscapes dataset.

Runs at over 100 FPS, enabling real-time applications.

Outperforms previous state-of-the-art methods in accuracy.

Abstract

In this paper, we present a novel neural network using multi scale feature fusion at various scales for accurate and efficient semantic image segmentation. We used ResNet based feature extractor, dilated convolutional layers in downsampling part, atrous convolutional layers in the upsampling part and used concat operation to merge them. A new attention module is proposed to encode more contextual information and enhance the receptive field of the network. We present an in depth theoretical analysis of our network with training and optimization details. Our network was trained and tested on the Camvid dataset and Cityscapes dataset using mean accuracy per class and Intersection Over Union (IOU) as the evaluation metrics. Our model outperforms previous state of the art methods on semantic segmentation achieving mean IOU value of 74.12 while running at >100 FPS.