Perceptual parsing for extracting semantic information from images.
Loading...
Journal Title
Journal ISSN
Volume Title
Perustieteiden korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Author
Date
2021-01-25
Department
Major/Subject
Machine Learning, Data Science and Artificial Intelligence
Mcode
SCI3044
Degree programme
Master’s Programme in Computer, Communication and Information Sciences
Language
en
Pages
84
Series
Abstract
Extracting semantic information from images is a challenge that is hard to achieve with the traditional software engineering approach. However, recent development in deep neural networks allows extracting semantic annotations affordably and efficiently. This work covers building a semantic segmentation model using a multi-task learning approach. The model is able to classify an image based on a scene and extract semantic information about objects present in an image, parts of those objects, as well as annotations about material and texture at a pixel level. A heterogeneous dataset is used to successfully train the model, which unifies five different datasets. Unlike conventional training of segmentation models, this research implements a concept called super-convergence, in which training time is reduced by at least 50%, yet the performance is not compromised. Many points discussed in this research paper are investigative. They aim to reach the main goal: building a segmentation model, efficiently training it, and producing a good semantic annotation of a given image. This work includes extensive information about the sequential progress to achieve this goal, starting with a literature review and ending with the model's implementation.Description
Supervisor
Ilin, AlexanderThesis advisor
Vanhala, JanneKeywords
semantic segmentation, image parsing, labeling, deep neural network, machine learning
