CISPA
Browse

File(s) not publicly available

Accurate and Diverse Sampling of Sequences Based on a ``Best of Many'' Sample Objective

conference contribution
posted on 2023-11-29, 18:08 authored by Apratim Bhattacharyya, Bernt Schiele, Mario FritzMario Fritz
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 has been formalized as a sequence extrapolation problem, where a number of observations are used to predict the sequence into the future. Real-world scenarios demand a model of uncertainty of such predictions, as predictions become increasingly uncertain -- in particular on long time horizons. While impressive results have been shown on point estimates, scenarios that induce multi-modal distributions over future sequences remain challenging. Our work addresses these challenges in a Gaussian Latent Variable model for sequence prediction. Our core contribution is a ``Best of Many'' sample objective that leads to more accurate and more diverse predictions that better capture the true variations in real-world sequence data. Beyond our analysis of improved model fit, our models also empirically outperform prior work on three diverse tasks ranging from traffic scenes to weather data.

History

Preferred Citation

Apratim Bhattacharyya, Bernt Schiele and Mario Fritz. Accurate and Diverse Sampling of Sequences Based on a ``Best of Many'' Sample Objective. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018.

Primary Research Area

  • Trustworthy Information Processing

Secondary Research Area

  • Secure Connected and Mobile Systems

Name of Conference

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Legacy Posted Date

2018-05-04

Open Access Type

  • Gold

BibTeX

@inproceedings{cispa_all_2597, title = "Accurate and Diverse Sampling of Sequences Based on a ``Best of Many'' Sample Objective", author = "Bhattacharyya, Apratim and Schiele, Bernt and Fritz, Mario", booktitle="{IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}", year="2018", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC