From KL Divergence to Wasserstein Distance: Enhancing Autoencoders with FID Analysis

Variational Autoencoders (VAEs) are popular Bayesian inference models that excel at approximating complex data distributions in a lower-dimensional latent space. Despite their widespread use, VAEs frequently face challenges in image generation, often resulting in blurry outputs. This outcome is pri...

Full description

Saved in:
Bibliographic Details
Main Authors: Laxmi Kanta Poudel, Kshtiz Aryal, Rajendra Bahadur Thapa, Sushil Poudel
Format: Article
Language:English
Published: LibraryPress@UF 2025-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Online Access:https://journals.flvc.org/FLAIRS/article/view/139006
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Variational Autoencoders (VAEs) are popular Bayesian inference models that excel at approximating complex data distributions in a lower-dimensional latent space. Despite their widespread use, VAEs frequently face challenges in image generation, often resulting in blurry outputs. This outcome is primarily attributed to two factors: the inherent probabilistic nature of the VAE framework and the oversmoothing effect induced by the Kullback-Leibler (KL) divergence term in the loss function. This paper explores the integration of Wasser- stein Distance into the VAEs framework, resulting in a Wasserstein Autoencoders (WAEs) designed to mit- igate the oversmoothing issue and enhance the qual- ity of generated images. We evaluated the proposed WAEs using the Fr´echet Inception Distance (FID), In- ception Score (IS) and Structural Similarity Index Mea- sure (SSIM). The experimental results in the CelebA dataset demonstrate that WAEs significantly outperform VAEs by 25% in FID, 13.6% in IS and 15.3% in SSIM. Additionally, the evaluation considers the issue of class imbalance in the ODIR dataset, where WAEs demon- strate superior accuracy and precision in classification tasks. Our findings highlight WAEs as a practical and efficient alternative to VAEs for image generation and reconstruction, particularly in resource-limited settings
ISSN:2334-0754
2334-0762