paper-with-me

홈 › Papers

Optimizing Hierarchical Image VAEs for Sample Quality

2022-10-18 · Eric Luhman, Troy Luhman

While hierarchical variational autoencoders (VAEs) have achieved great density estimation on image modeling tasks, samples from their prior tend to look less convincing than models with similar log-likelihood. We attribute this to learned representations that over-emphasize compressing imperceptible details of the image. To address this, we introduce a KL-reweighting strategy to control the amount of infor mation in each latent group, and employ a Gaussian output layer to reduce sharpness in the learning objective. To trade off image diversity for fidelity, we additionally introduce a classifier-free guidance strategy for hierarchical VAEs. We demonstrate the effectiveness of these techniques in our experiments. Code is available at https://github.com/tcl9876/visual-vae.

📄 PDF Abstract BibTeX arXiv:2210.10205

Code (1)

tcl9876/visual-vae 공식 구현 jax

Tasks

AttributeDensity EstimationDiversity

Similar Papers 제목 키워드 기반

NCP-VAE: Variational Autoencoders with Noise Contrastive Priors

2020-09-28 · Jyoti Aneja, Alex Schwing, Jan Kautz, Arash Vahdat

Variational autoencoders (VAEs) are one of the powerful likelihood-based generative models with applications in various domains. However, they struggle to generate high-quality images, especially when samples are obtaine…

A Contrastive Learning Approach for Training Variational Autoencoder Priors

2020-10-06 · NeurIPS 2021 12 · Jyoti Aneja, Alexander Schwing, Jan Kautz, Arash Vahdat

Variational autoencoders (VAEs) are one of the powerful likelihood-based generative models with applications in many domains. However, they struggle to generate high-quality images, especially when samples are obtained f…

Contrastive LearningImage Generation

Hierarchical Quantized Autoencoders

2020-02-19 · NeurIPS 2020 12 · Will Williams, Sam Ringer, Tom Ash, John Hughes 외

Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates. Encouraged by recent success in learning d…

Image CompressionQuantization

Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images

2020-11-20 · ICLR 2021 1 · Rewon Child

We present a hierarchical VAE that, for the first time, generates samples quickly while outperforming the PixelCNN in log-likelihood on all natural image benchmarks. We begin by observing that, in theory, VAEs can actual…

Image Generation

Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection

2025-06-11 · Dane Williamson, Yangfeng Ji, Matthew Dwyer

Out-of-distribution (OOD) detection is a critical task in machine learning, particularly for safety-critical applications where unexpected inputs must be reliably flagged. While hierarchical variational autoencoders (HVA…

Out of Distribution (OOD) Detection