Towards Explainability of the Latent Space by Disentangled Representation Learning

Autor: Ivars Namatēvs, Artūrs Ņikuļins, Anda Slaidiņa, Laura Neimane, Oskars Radziņš, Kaspars Sudars
Jazyk: angličtina
Rok vydání: 2023
Předmět:
Zdroj: Information Technology and Management Science, Vol 26, Iss 1, Pp 41-48 (2023)
Druh dokumentu: article
ISSN: 2255-9094
DOI: 10.7250/itms-2023-0006
Popis: Deep neural networks are widely used in computer vision for image classification, segmentation and generation. They are also often criticised as “black boxes” because their decision-making process is often not interpretable by humans. However, learning explainable representations that explicitly disentangle the underlying mechanisms that structure observational data is still a challenge. To further explore the latent space and achieve generic processing, we propose a pipeline for discovering the explainable directions in the latent space of generative models. Since the latent space contains semantically meaningful directions and can be explained, we propose a pipeline to fully resolve the representation of the latent space. It consists of a Dirichlet encoder, conditional deterministic diffusion, a group-swap and a latent traversal module. We believe that this study provides an insight into the advancement of research explaining the disentanglement of neural networks in the community.
Databáze: Directory of Open Access Journals