Optimizing Hierarchical Image VAEs for Sample Quality
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.
Code (1)
Tasks
AttributeDensity EstimationDiversitySimilar Papers 제목 키워드 기반
NCP-VAE: Variational Autoencoders with Noise Contrastive Priors
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
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 GenerationHierarchical Quantized Autoencoders
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 CompressionQuantizationVery Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
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 GenerationOptimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection
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