智能感知与计算系列讲座
Lecture Series in Intelligent Perception and Computing 

题    目 （TITLE）：Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View

讲 座 人 （SPEAKER）: 王玉旺 高级研究员，微软亚洲研究院

主 持 人 (CHAIR)：张兆翔 研究员

时    间 (TIME)：2022年3月18日（周五），10：00

地    点 (VENUE)： 腾讯会议ID: 428 444 730 Password: 2022

报告摘要（ABSTRACT）：

From the intuitive notion of disentanglement, the image variations from different generative factors should be distinct from each other, and the disentangled representation should reflect those variations with separate dimensions. To discover the generative factors and learn disentangled representation, previous methods typically leverage an extra regularization term when learning to generate realistic images. However, the term usually results in a trade-off between disentanglement and generation quality. For the generative models pretrained without any disentanglement term, the generated images show semantically meaningful variations when traversing along different directions in the latent space. Based on this observation, we argue that it is possible to mitigate the trade-off by (i) leveraging the pretrained generative models with high generation quality, (ii) focusing on discovering the traversal directions as generative factors for disentangled representation learning. To achieve this, we propose Disentaglement via Contrast (DisCo) as a framework to model the variations based on the target disentangled representations, and contrast the variations to jointly discover disentangled directions and learn disentangled representations. DisCo achieves the state-of-the-art disentangled representation learning and distinct direction discovering, given pretrained non-disentangled generative models including GAN, VAE, and Flow.

报告人简介（BIOGRAPHY）：

王玉旺，微软亚洲研究院高级研究员，博士毕业于清华大学自动化系，博士导师为戴琼海院士。研究方向为，解耦表征学习，3D视觉等。在CVPR，ICCV，ICLR等国际顶级会议发表多篇论文，并担任CVPR，ICCV，TPAMI，TVCG的审稿工作。