Repository logo
 

Transformer, diffusion, and GAN-based augmentations for contrastive learning of visual representations

dc.contributor.authorArmstrong, Samuel, author
dc.contributor.authorPallickara, Sangmi, advisor
dc.contributor.authorPallickara, Shrideep, advisor
dc.contributor.authorGhosh, Sudipto, committee member
dc.contributor.authorBreidt, F. Jay, committee member
dc.date.accessioned2024-05-27T10:32:53Z
dc.date.available2024-05-27T10:32:53Z
dc.date.issued2024
dc.description.abstractGenerative modeling and self-supervised learning have emerged as two of the most prominent fields of study in machine learning in recent years. Generative models are able to learn detailed visual representations that can then be used to generate synthetic data. Modern self-supervised learning methods are able to extract high-level visual information from images in an unsupervised manner and then apply this information to downstream tasks such as object detection and segmentation. As generative models become more and more advanced, we want to be able to extract their learned knowledge and then apply it to downstream tasks. In this work, we develop Generative Contrastive Learning (GCL), a methodology that uses contrastive learning to extract information from modern generative models. We define GCL's high-level components: an encoder, feature map augmenter, decoder, handcrafted augmenter, and contrastive learning model and demonstrate how to apply GCL to the three major types of large generative models: GANs, Diffusion Models, and Image Transformers. Due to the complex nature of generative models and the near-infinite number of unique images they can produce, we have developed several methodologies to synthesize images in a manner that compliments the augmentation-based learning that is used in contrastive learning frameworks. Our work shows that applying these large generative models to self-supervised learning can be done in a computationally viable manner without the use of large clusters of high-performance GPUs. Finally, we show the clear benefit of leveraging generative models in a contrastive learning setting using standard self-supervised learning benchmarks.
dc.format.mediumborn digital
dc.format.mediumdoctoral dissertations
dc.identifierArmstrong_colostate_0053A_18287.pdf
dc.identifier.urihttps://hdl.handle.net/10217/238504
dc.languageEnglish
dc.language.isoeng
dc.publisherColorado State University. Libraries
dc.relation.ispartof2020-
dc.rightsCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.
dc.subjectgenerative models
dc.subjectmachine learning
dc.subjectself-supervised learning
dc.subjectlearning representations
dc.subjectcomputer vision
dc.subjectneural networks
dc.titleTransformer, diffusion, and GAN-based augmentations for contrastive learning of visual representations
dc.typeText
dcterms.rights.dplaThis Item is protected by copyright and/or related rights (https://rightsstatements.org/vocab/InC/1.0/). You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
thesis.degree.disciplineComputer Science
thesis.degree.grantorColorado State University
thesis.degree.levelDoctoral
thesis.degree.nameDoctor of Philosophy (Ph.D.)

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Armstrong_colostate_0053A_18287.pdf
Size:
3.26 MB
Format:
Adobe Portable Document Format