L-VAE: Variational Auto-Encoder with Learnable Beta for Disentangled Representation
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Advanced PID Control2026
- Multi-level feature disentanglement network for cross-dataset face forgery detectionImage and Vision Computing, 2023
- Measuring Disentanglement: A Review of MetricsIEEE Transactions on Neural Networks and Learning Systems, 2022
- ControlVAE: Tuning, Analytical Properties, and Performance AnalysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Understanding deep learning (still) requires rethinking generalizationCommunications of the ACM, 2021
- Face identity disentanglement via latent space mappingACM Transactions on Graphics, 2020
- Diverse Image-to-Image Translation via Disentangled Representations2018
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013