Generative model based approaches to learning with incomplete supervision

Date

2023-12-05

Author

Gençoğlu, Sinan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

256
views

64
downloads

Cite This

The developments in deep learning have led to great advances in a variety of recogni- tion problems. However, predominantly the state-of-the-art models rely on the avail- ability of large annotated training sets. Therefore, great attention has recently shifted to developing models that can incorporate concepts of interest in the absence of care- fully annotated large training sets for them. Commonly referred to as learning with limited supervision, these methods vary from completely unsupervised learning to model training with noisy labels. In this thesis, we focus on the problem of learning classification models of novel classes based on a small number of training examples, also known as few-shot learning. We approach this problem from a generative per- spective, where we first aim to learn a generative model and then we explore the effect of the generative model on a few-shot classification task. The primary focus of this study revolves around a generative model that is founded on diffusion principles and incorporates a transformer to manipulate latent patches. This model functions by uti- lizing image features acquired from a pre-trained feature extractor as its conditional input. As a result of adopting this methodology, we provide an empirical assessment of the generative model’s efficacy within a few-shot learning scenario

Subject Keywords

Generative Models, Sample-generating, Few-shot Learning

URI

https://hdl.handle.net/11511/106386

Collections

Graduate School of Natural and Applied Sciences, Thesis