ResearchTrend.AI
  • Papers
  • Communities
  • Organizations
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1612.00197
113
185
v1v2v3 (latest)

Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses

1 December 2016
Christian Rupprecht
Iro Laina
R. DiPietro
Maximilian Baust
Federico Tombari
Nassir Navab
ArXiv (abs)PDFHTML
Abstract

Many prediction tasks contain uncertainty. In the case of next-frame or future prediction the uncertainty is inherent in the task itself, as it is impossible to foretell what exactly is going to happen in the future. Another source of uncertainty or ambiguity is the way data is labeled. Sometimes not all objects of interest are annotated in a given image or the annotation is ambiguous, e.g. in the form of occluded joints in human pose estimation. We present a method that is able to handle these problems by predicting not a single output but multiple hypotheses. More precisely, we propose a framework for re-formulating existing single prediction models as multiple hypothesis prediction (MHP) problems as well as a meta loss and an optimization procedure to train the resulting MHP model. We consider three entirely different applications, i.e. future prediction, image classification and human pose estimation, and demonstrate how existing single hypothesis predictors (SHPs) can be turned into MHPs. The performed experiments show that the resulting MHP outperforms the existing SHP and yields additional insights regarding the variation and ambiguity of the predictions.

View on arXiv
Comments on this paper