Conditional Flow Variational Autoencoders for Structured Sequence Prediction

08/24/2019
by   Apratim Bhattacharyya, et al.
22

Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for structured sequence prediction based on latent variable models imposes a uni-modal standard Gaussian prior on the latent variables. This induces a strong model bias which makes it challenging to fully capture the multi-modality of the distribution of the future states. In this work, we introduce Conditional Flow Variational Autoencoders which uses our novel conditional normalizing flow based prior. We show that using our novel complex multi-modal conditional prior we can capture complex multi-modal conditional distributions. Furthermore, we study for the first time latent variable collapse with normalizing flows and propose solutions to prevent such failure cases. Our experiments on three multi-modal structured sequence prediction datasets -- MNIST Sequences, Stanford Drone and HighD -- show that the proposed method obtains state of art results across different evaluation metrics.

READ FULL TEXT

page 2

page 6

page 7

page 11

page 12

page 14

research
06/18/2018

Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization

For autonomous agents to successfully operate in the real world, anticip...
research
08/23/2019

Increasing the Generalisaton Capacity of Conditional VAEs

We address the problem of one-to-many mappings in supervised learning, w...
research
06/20/2018

Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective

For autonomous agents to successfully operate in the real world, anticip...
research
03/22/2019

Multi-modal Probabilistic Prediction of Interactive Behavior via an Interpretable Model

For autonomous agents to successfully operate in real world, the ability...
research
10/01/2018

Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods

For autonomous agents to successfully operate in the real world, the abi...
research
10/20/2020

Variational Dynamic Mixtures

Deep probabilistic time series forecasting models have become an integra...
research
11/30/2020

RegFlow: Probabilistic Flow-based Regression for Future Prediction

Predicting future states or actions of a given system remains a fundamen...

Please sign up or login with your details

Forgot password? Click here to reset