English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization

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.

Item is

Files

show Files
hide Files
:
arXiv:1806.06939.pdf (Preprint), 9MB
Name:
arXiv:1806.06939.pdf
Description:
File downloaded from arXiv at 2018-07-02 14:01
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Bhattacharyya, Apratim1, Author           
Fritz, Mario1, Author           
Schiele, Bernt1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG
 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.

Details

show
hide
Language(s): eng - English
 Dates: 2018-06-182018
 Publication Status: Published online
 Pages: 14 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1806.06939
URI: http://arxiv.org/abs/1806.06939
BibTex Citekey: Bhattacharyya_arXiv1806.06939
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show