In the last decade, substantial progress has been made w.r.t. the performance of computer vision systems, a significant part of it thanks to deep learning. These advancements prompted sharp community growth and a rise in industrial investment. However, most current models lack the ability to reason about the confidence of their predictions; integrating uncertainty quantification into vision systems will help recognize failure scenarios and enable robust applications.

In addition to advances in Bayesian deep learning, providing practical approaches for vision problems, the workshop will provide a forum for discussing promising research directions, which have received less attention, as well as advancing current practices to drive future research. Examples include: the development of new metrics that reflect the real-world need for uncertainty when using vision systems with down-stream tasks; and moving beyond point-estimates to address the multi-modal ambiguities inherent in many vision tasks.

This years UNcertainty quantification for Computer Vision (UNCV) Workshop aims to raise awareness and generate discussion regarding how predictive uncertainty can, and should, be effectively incorporated into models within the vision community. The workshop will bring together experts from machine learning and computer vision to create a new generation of well-calibrated and effective methods that know when they do not know.


Workshop Program

The workshop will happen in person at the MiCo in Milan. Exact location will be announced in time.

Call for Papers

The ECCV 2024 workshop on Uncertainty Quantification for Computer Vision will consider recent advances in methodology and applications of uncertainty quantification in computer vision. Prospective authors are invited to submit papers or extended abstracts on relevant algorithms and applications including, but not limited to:

  • Applications of uncertainty quantification
  • Failure prediction (e.g., OOD detection)
  • Robustness in CV
  • Safety critical applications in CV
  • Domain-shift in CV
  • Probabilistic deep models
  • Deep probabilistic models
  • Deep ensemble uncertainty
  • Connections between NNs and GPs
  • Incorporating explicit prior knowledge in deep learning
  • Computational aspects and real-time probabilistic inference
  • Output ambiguity, multi-modality and diversity

We invite three types of submissions: workshop papers (14 pages), extended abstracts (4 pages), and papers accepted at ECCV 2024.

All submissions will be peer-reviewed, and accepted submissions will be presented at the workshop. Only accepted ECCV workshop papers (14 pages) will be included in the ECCV Workshop Proceedings.

See submission instructions for details.

Important Dates

All times are end of day AOE.

  • Submission deadline: 17/07/2024
  • Notification of acceptance: 20/08/2024
  • Camera-ready deadline: 31/08/2024

Previous Workshops