Fatos T. Yarman-Vural
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fatos T. Yarman-Vural has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Hazal Mogultay Ozcan
Computer Engineering, Middle East Technical Universty, Ankara, Turkey
2 shared publications - Sinan Kalkan
Middle East Technical University
2 shared publications
Latest Publications
- 24 July 2025
- Published by Springer Nature in Machine Vision and Applications
- Vol. 36 (5) , 1-14
L-VAE: variational auto-encoder with learnable beta for disentangled representation
- 24 July 2025
- Published by Springer Nature in Machine Vision and Applications
- Vol. 36 (5) , 1-14
L-VAE: variational auto-encoder with learnable beta for disentangled representation
- Open Access
L-VAE: Variational Auto-Encoder with Learnable Beta for Disentangled Representation
In this paper, we propose a novel model called Learnable VAE (L-VAE), which learns a disentangled representation together with the hyperparameters of the cost function. L-VAE can be considered as an extension of \b{eta}-VAE, wherein the hyperparameter, \b{eta}, is empirically adjusted. L-VAE mitigates the limitations of \b{eta}-VAE by learning the relative weights of the terms in the loss function to control the dynamic trade-off between disentanglement and reconstruction losses. In the proposed model, the weight of the loss terms and the parameters of the model architecture are learned concurrently. An additional regularization term is added to the loss function to prevent bias towards either reconstruction or disentanglement losses. Experimental analyses show that the proposed L-VAE finds an effective balance between reconstruction fidelity and disentangling the latent dimensions. Comparisons of the proposed L-VAE against \b{eta}-VAE, VAE, ControlVAE, DynamicVAE, and σ-VAE on datasets, such as dSprites, MPI3D-complex, Falcor3D, and Isaac3D reveals that L-VAE consistently provides the best or the second best performances measured by a set of disentanglement metrics. Moreover, qualitative experiments on CelebA dataset, confirm the success of the L-VAE model for disentangling the facial attributes.
Open AccessL-VAE: Variational Auto-Encoder with Learnable Beta for Disentangled Representation
In this paper, we propose a novel model called Learnable VAE (L-VAE), which learns a disentangled representation together with the hyperparameters of the cost function. L-VAE can be considered as an extension of \b{eta}-VAE, wherein the hyperparameter, \b{eta}, is empirically adjusted. L-VAE mitigates the limitations of \b{eta}-VAE by learning the relative weights of the terms in the loss function to control the dynamic trade-off between disentanglement and reconstruction losses. In the proposed model, the weight of the loss terms and the parameters of the model architecture are learned concurrently. An additional regularization term is added to the loss function to prevent bias towards either reconstruction or disentanglement losses. Experimental analyses show that the proposed L-VAE finds an effective balance between reconstruction fidelity and disentangling the latent dimensions. Comparisons of the proposed L-VAE against \b{eta}-VAE, VAE, ControlVAE, DynamicVAE, and σ-VAE on datasets, such as dSprites, MPI3D-complex, Falcor3D, and Isaac3D reveals that L-VAE consistently provides the best or the second best performances measured by a set of disentanglement metrics. Moreover, qualitative experiments on CelebA dataset, confirm the success of the L-VAE model for disentangling the facial attributes.