Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
Thesis_draft_Rachel - JA LW final format approved 8.4.20.pdf (5.25 MB)
ETD Abstract Container
Abstract Header
Semi Supervised Learning for Accurate Segmentation of Roughly Labeled Data
Author Info
Rajan, Rachel
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1597082270750151
Abstract Details
Year and Degree
2020, Master of Science (M.S.), University of Dayton, Electrical and Computer Engineering.
Abstract
Recent advancements in Neural Networks have obtained immense popularity in the field of computer vision applications including image classification, semantic segmentation, object detection and many more. Studies show that semantic segmentation has always been a challenging task in computer vision. This requires a significantly number of pixel-level annotated to assign a label to each image pixel. But, for supervised deep learning techniques, the unavailability of labeled data has limited applications for accurate semantic segmentation. Hence, an enhanced adversarial learning approach in semi-supervised segmentation is proposed for incremental training of the deep learning-based model to utilize unlabeled data in achieving better learning performance. Studies reveal that unlabeled data combined with small amount of labeled data can improve the overall performance considerably. Since most of the existing methods use weakly labeled images, the proposed technique utilizes unlabeled instances to improve the segmentation model. A Generative and Adversarial Network (GAN) based semi-supervised framework is implemented here. This mainly consists of a generator and a discriminator, the generator provides extra training examples to classifier, while the discriminator works on providing labels to the samples from the possible classes else assigns it as a pseudo label. The main motive of this implementation is to adding large pseudo labels turns the real samples to be closer in the feature space hence improving the pixel level classification. Experiments on a publicly available datasets such as PASCAL VOC 2012 and PODOCYTE Benchmark dataset released by University at Buffalo, which demonstrate the effectiveness of the proposed method.
Committee
Vijayan Asari, Dr. (Advisor)
Pages
53 p.
Subject Headings
Computer Engineering
Keywords
Semantic Segmentation, Semi-supervised Learning, Generative Adversarial Networks, Encoder-decoder, Computer Vision
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Rajan, R. (2020).
Semi Supervised Learning for Accurate Segmentation of Roughly Labeled Data
[Master's thesis, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1597082270750151
APA Style (7th edition)
Rajan, Rachel.
Semi Supervised Learning for Accurate Segmentation of Roughly Labeled Data .
2020. University of Dayton, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1597082270750151.
MLA Style (8th edition)
Rajan, Rachel. "Semi Supervised Learning for Accurate Segmentation of Roughly Labeled Data ." Master's thesis, University of Dayton, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1597082270750151
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
dayton1597082270750151
Download Count:
327
Copyright Info
© 2020, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.