Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars
Authors:
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2650-2656
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 down-sampling 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.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Instance-Sensitive Fully Convolutional Networks2016
- Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation2016
- Semantic Image Segmentation via Deep Parsing Network2015
- Conditional Random Fields as Recurrent Neural Networks2015
- Learning Deconvolution Network for Semantic Segmentation2015
- Multiclass semantic video segmentation with object-level active inference2015
- Going deeper with convolutions2015
- Fully convolutional networks for semantic segmentation2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009