SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.10205 · 2022

Optimizing Hierarchical Image VAEs for Sample Quality

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.10205")
get_code_for_paper("2210.10205")
have("2210.10205")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.10205.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.10205.svg)](https://syntology.ai/paper/2210.10205)

Connect an agent — have() is free.