2023/09/22 by Mariano Rivera, Rivera, Mariano · 2 voices
Computer Science · #68T07 #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #Gaussian #I.2.4 #I.4.5 #Machine Learning (cs.LG) #Mixture model #Pattern recognition (psychology) #Physics #cs.AI #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2309.13160
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/09/22 · arxiv published 2023/09/22 · openalex created_date 2023/09/27 · arxiv updated 2024/06/21 · openalex updated_date 2026/07/28
Variational Autoencoders (VAEs) have become a cornerstone in generative modeling and representation learning within machine learning. This paper explores a nuanced aspect of VAEs, focusing on interpreting the Kullback-Leibler (KL) Divergence, a critical component within the Evidence Lower Bound (ELBO) that governs the trade-off between reconstruction accuracy and regularization. Meanwhile, the KL Divergence enforces alignment between latent variable distributions and a prior imposing a structure on the overall latent space but leaves individual variable distributions unconstrained. The proposed method redefines the ELBO with a mixture of Gaussians for the posterior probability, introduces a regularization term to prevent variance collapse, and employs a PatchGAN discriminator to enhance texture realism. Implementation details involve ResNetV2 architectures for both the Encoder and Decoder. The experiments demonstrate the ability to generate realistic faces, offering a promising solution for enhancing VAE-based generative models.