arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.03023cs.LGcs.CV
收藏

基于对比潜变量的能量引导模型

Guiding Energy-based Models via Contrastive Latent Variables

LG AI Research(LG人工智能研究院);KAIST(韩国科学技术院);Korea University(高丽大学)

Hankook Lee, Jongheon Jeong, Sejun Park, Jinwoo Shin

摘要:

基于能量的模型(EBM)是一种流行的生成框架,它提供了显式的密度和架构灵活性,但训练它们是困难的,因为它通常是不稳定和耗时的。近年来,已经开发了各种训练技术,例如,更好的发散性措施或MCMC采样中的稳定性,但在生成质量方面,EBM和其他生成框架(如GANs)之间往往存在很大的差距。在本文中,我们提出了一个新的和有效的框架,通过对比表示学习(CRL),以改善EBM。具体来说,我们认为通过对比方法学习的表征是真正的潜在变量。这种对比潜变量可以引导循证医学人员更好地理解数据结构,从而显著地提高和加快循证医学培训。为了实现EBM和CRL的联合训练,我们还设计了一类新的潜变量EBM,用于学习数据和对比潜变量的联合密度。我们的实验结果表明,与现有技术的EBM方法(例如,附加地使用变分自编码器或扩散技术),甚至具有显著更快和更有存储效率的训练。我们还展示了潜变量EBM的条件和合成生成能力作为其额外的好处,即使没有明确的条件训练。该代码可在https://github.com/hankook/CLEL上获得。

英文摘要:

An energy-based model (EBM) is a popular generative framework that offers both explicit density and architectural flexibility, but training them is difficult since it is often unstable and time-consuming. In recent years, various training techniques have been developed, e.g., better divergence measures or stabilization in MCMC sampling, but there often exists a large gap between EBMs and other generative frameworks like GANs in terms of generation quality. In this paper, we propose a novel and effective framework for improving EBMs via contrastive representation learning (CRL). To be specific, we consider representations learned by contrastive methods as the true underlying latent variable. This contrastive latent variable could guide EBMs to understand the data structure better, so it can improve and accelerate EBM training significantly. To enable the joint training of EBM and CRL, we also design a new class of latent-variable EBMs for learning the joint density of data and the contrastive latent variable. Our experimental results demonstrate that our scheme achieves lower FID scores, compared to prior-art EBM methods (e.g., additionally using variational autoencoders or diffusion techniques), even with significantly faster and more memory-efficient training. We also show conditional and compositional generation abilities of our latent-variable EBMs as their additional benefits, even without explicit conditional training. The code is available at https://github.com/hankook/CLEL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑