English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization

MPS-Authors
/persons/resource/persons197297

Bhattacharyya,  Apratim
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

/persons/resource/persons44451

Fritz,  Mario
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1806.06939.pdf
(Preprint), 9MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Bhattacharyya, A., Fritz, M., & Schiele, B. (2018). Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization. Retrieved from http://arxiv.org/abs/1806.06939.


Cite as: http://hdl.handle.net/21.11116/0000-0001-997B-9
Abstract
For autonomous agents to successfully operate in the real world, anticipation of future events and states of their environment is a key competence. This problem can be formalized as a sequence prediction problem, where a number of observations are used to predict the sequence into the future. However, real-world scenarios demand a model of uncertainty of such predictions, as future states become increasingly uncertain and multi-modal -- in particular on long time horizons. This makes modelling and learning challenging. We cast state of the art semantic segmentation and future prediction models based on deep learning into a Bayesian formulation that in turn allows for a full Bayesian treatment of the prediction problem. We present a new sampling scheme for this model that draws from the success of variational autoencoders by incorporating a recognition network. In the experiments we show that our model outperforms prior work in accuracy of the predicted segmentation and provides calibrated probabilities that also better capture the multi-modal aspects of possible future states of street scenes.