Thumbnail Image
Item

kFactorVAE: Self-Supervised Regularization for Better A.I. Disentanglement

Lee, Joseph S.
Abstract
Obtaining disentangled representations is a goal sought after to make A.I. models more interpretable. Studies have proven the impossibility of obtaining these kinds of representations with just unsupervised learning, or in other words, without strong inductive biases. One strong inductive bias is a regularization term that encourages the invariance of factors of variations across an image and a carefully selected augmentation. In this thesis, we build upon the existing Variational Autoencoder (VAE)-based disentanglement literature by utilizing the aforementioned inductive bias. We evaluate our method on the dSprites dataset, a well-known benchmark, and demonstrate its ability to achieve comparable or higher disentanglement in significantly fewer training steps against our model’s unsupervised counterparts.
Description
Date
2023-05-01
Journal Title
Journal ISSN
Volume Title
Publisher
Collections
Undergraduate Honors Theses
Show all metadata
Download Dataset
Files
kFactorVAE.pdf
Adobe PDF, 2.42 MB
Rights Holder
Usage License
Embargo
Research Projects
Organizational Units
Journal Issue
Keywords
Citation
Advisor
Shao, Huajie
Li, Qun
Runfola, Daniel
Department
Computer Science
DOI
URI
https://scholarworks.wm.edu/handle/internal/11511
Embedded videos