Multi-Task Learning SegNet Architecture for Semantic Segmentation
Date of Award
2018
Degree Name
M.S. in Computer Engineering
Department
Department of Electrical and Computer Engineering
Advisor/Chair
Advisor: Vijayan Asari
Abstract
Semantic segmentation has been a complex problem in the field of computer vision and is essential for image analysis tasks. Currently, most state-of-the-art algorithms rely on deep convolutional neural networks (DCNN) to perform this task. DCNNs are able to down-sample the spatial resolution of the input image into low resolution feature mappings which are then up-sampled to produce the segmented images. However, the reduction of this spatial information causes the high frequency details of the image to be lessened resulting in blurry and inaccurate object boundaries. In order to improve this limitation, I propose combining a DCNN used for semantic segmentation with semantic boundary information. This is done using a multi-task approach by incorporating a boundary detection network into the encoder decoder architecture SegNet. I explore two different multi-task learning methods of incorporating this boundary information into the SegNet architecture. These two multi-task approaches are as follows: the incorporation of the global probability of boundary algorithm and the inclusion of an edge class. In doing so, the multi-task learning network is provided more information, thus improving segmentation accuracy, specifically boundary delineation. This approach was tested on the CityScapes dataset as well as the RGB-NIR Scene dataset. Compared to using SegNet alone, I observe increased boundary segmentation accuracies using this approach. I am able to show that the addition of a boundary detection information significantly improves the semantic segmentation results of a DCNN.
Keywords
Computer Engineering, Electrical Engineering, Artificial Intelligence, semantic segmentation, SegNet, scene labeling, boundary detection, multi-task learning
Rights Statement
Copyright © 2018, author
Recommended Citation
Sorg, Bradley R., "Multi-Task Learning SegNet Architecture for Semantic Segmentation" (2018). Graduate Theses and Dissertations. 6824.
https://ecommons.udayton.edu/graduate_theses/6824
