CONTEXT-INVARIANT AUTOENCODER TRAINING VIA UNSUPERVISED DOMAIN ADAPTATION

Date

2025-3-27

Author

Köktürk, Özge

Metadata

Show full item record

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

Item Usage Stats

47
views

0
downloads

Cite This

In practical use of machine learning models, generalizability is of crucial importance. When a model is trained on a dataset obtained in a specific context, it often performs poorly in similar situations but under different contexts. This can lead to unreliable predictions and potentially harmful decisions in real-life applications. This thesis proposes a training methodology for context-invariant autoencoders through unsupervised domain adaptation, aiming to learn representations that remain stable across varying contexts. Consequently, any application can be built on top of these domain-invariant representations. In this study, domain-adversarial training and data augmentation strategies have been employed to extract features that capture the essential structures of input images while disregarding features associated with contextual changes. For the experiments, image data collected from the CARLA (Car Learning to Act) simulator system under different weather conditions and various times of day have been used.

Subject Keywords

Context-Invariant Autoencoders, Unsupervised Domain Adaptation, Domain-Adversarial Training, Data Augmentation, CARLA Simulator

URI

https://hdl.handle.net/11511/114436

Collections

Graduate School of Informatics, Thesis