Nonparametric Variational Auto-encoders for Hierarchical Representation Learning
2017 IEEE International Conference on Computer Vision (ICCV)(2017)
摘要
The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the latent variables such as standard normal distribution, thereby restricting its applications to relatively simple phenomena. In this work, we propose hierarchical nonparametric variational autoencoders, which combines tree-structured Bayesian nonparametric priors with VAEs, to enable infinite flexibility of the latent representation space. Both the neural parameters and Bayesian priors are learned jointly using tailored variational inference. The resulting model induces a hierarchical structure of latent semantic concepts underlying the data corpus, and infers accurate representations of data instances. We apply our model in video representation learning. Our method is able to discover highly interpretable activity hierarchies, and obtain improved clustering accuracy and generalization capacity based on the learned rich representations.
更多查看译文
关键词
latent representation space,neural parameters,Bayesian priors,tailored variational inference,latent semantic concepts,video representation learning,nonparametric variational auto-encoders,hierarchical representation learning,neural networks,Bayesian methods,nonparametric variational autoencoders,tree-structured Bayesian nonparametric priors
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络