Doctoral Thesis Defense of Tobias Hinz
28 April 2021
Tobias Hinz successfully defended his doctoral thesis titled “Disentanglement, Compositionality, Specification: Representation Learning with Generative Adversarial Networks" on 28 April 2021. The thesis introduces novel approaches for learning good image representations with GANs and evaluates these representations on challenging tasks such as image generation and translation, text-to-image synthesis, and few-shot learning. The thesis shows that the three examined characteristics lead to meaningful improvements on many different tasks and points to several future directions in how these characteristics can be combined. Congratulations to Tobias by the Knowledge Technology team!