分离解码器方差与β参数，解决VAE生成图像模糊问题
Beta-Sigma VAE: Separating beta and decoder variance in Gaussian variational autoencoder
- 显式分离β和解码器方差σ²ˣ，避免参数混淆
- 在自然图像生成上表现更优，且可预测分析结果
- 适合关注生成质量与模型可解释性的研究者
变分自编码器（VAE）是经典的生成模型，但普遍存在输出模糊的问题。本文深入探究该问题，发现解码器的高斯方差与β参数在随机似然值下难以区分，阻碍了模型分析并限制了性能提升。为此，提出Beta-Sigma VAE（BS-VAE），显式分离β与解码器方差σ²ˣ。实验表明，该方法在自然图像合成任务中表现更优，同时具备可控参数与可预测的分析能力。评估使用率失真曲线与计算机视觉数据集上的代理指标，代码已开源。
原文摘要 · Abstract (English)
Variational autoencoder (VAE) is an established generative model but is notorious for its blurriness. In this work, we investigate the blurry output problem of VAE and resolve it, exploiting the variance of Gaussian decoder and $β$ of beta-VAE. Specifically, we reveal that the indistinguishability of decoder variance and $β$ hinders appropriate analysis of the model by random likelihood value, and limits performance improvement by omitting the gain from $β$. To address the problem, we propose Beta-Sigma VAE (BS-VAE) that explicitly separates $β$ and decoder variance $σ^2_x$ in the model. Our method demonstrates not only superior performance in natural image synthesis but also controllable parameters and predictable analysis compared to conventional VAE. In our experimental evaluation, we employ the analysis of rate-distortion curve and proxy metrics on computer vision datasets. The code is available on https://github.com/overnap/BS-VAE
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。