mlsanityData to 14 Oct 2026

How to train your VAE

arXiv 2309.13160 ↗First posted 22 Sep 2023cs.LG cs.AI cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 22 Sep 2023.

Builds on

16 of 22 references.

References · 16

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  2. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  3. 2015Variational Inference with Normalizing Flowscited by 2,170
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  5. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  6. 2019An Introduction to Variational Autoencoderscited by 1,000
  7. 2017Generative Adversarial Networks: An Overviewcited by 590
  8. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  9. 2017Wasserstein Auto-Encoderscited by 373
  10. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  11. 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
  12. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
4 more
  1. 2019Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGANcited by 87
  2. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  3. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  4. 2021Preventing Oversmoothing in VAE via Generalized Variance Parameterizationcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusioncited by 17
  2. 2025A Multi-Agent Framework Integrating Large Language Models and Generative AI for Accelerated Metamaterial Designcited by 3
  3. 2026FedGMI: Generative Model-Driven Federated Learning for Probabilistic Mixture Inferencecited by 0