S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation

Abstract

We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e.g., videos and audios) under self-supervision. Specifically, we exploit the benefits of some readily accessible supervisory signals from input data itself or some off-the-shelf functional models and accordingly design auxiliary tasks for our model to utilize these signals. With the supervision of the signals, our model can easily disentangle the representation of an input sequence into static factors and dynamic factors (i.e., time-invariant and time-varying parts). Comprehensive experiments across videos and audios verify the effectiveness of our model on representation disentanglement and generation of sequential data, and demonstrate that, our model with self-supervision performs comparable to, if not better than, the fully-supervised model with ground truth labels, and outperforms state-of-the-art unsupervised models by a large margin.

to appear in CVPR2020

References in corpus (6)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• The Kinetics Human Action Video Dataset
• Decomposing Motion and Content for Natural Video Sequence Prediction
• Learning Stochastic Recurrent Networks
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Variational Recurrent Auto-Encoders