Uncertainty Quantification for Computer Vision Call for Papers
********************************
Call for Papers
Uncertainty Quantification for Computer Vision
Workshop & Challenge at CVPR 2025 (4th Edition)
https://uncertainty-cv.github.io/2025/
********************************
Submission Deadline Mar 14th AOE
Two types of paper are welcome:
- Regular Papers -
(novel contributions not published previously)
- Extended Abstracts -
(novel contributions or papers that have been already accepted for publication previously)
----------------------------
Apologies for multiple posting
Please distribute this call to interested parties
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.
The CVPR 2025 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 on relevant algorithms and applications
including, but not limited to:
Applications of uncertainty quantification in computer vision
Reliability of Multi-modal Models (e.g., Vision-Language)
Uncertainty Quantification of Open-Vocabulary approaches
Failure prediction (e.g., Out-of-Distribution detection)
Robustness in computer vision
Safety critical applications (e.g., autonomous driving, medical diagnosis)
Domain-shift in computer vision
Deep probabilistic models
Methods for uncertainty quantification
Incorporating explicit prior knowledge in deep learning
Output ambiguity, label noise, and diversity
Uncertainty Quantification of GenAI approaches
All papers will be peer-reviewed, and accepted Regular papers are presented at the workshop and included in the CVPR Workshop Proceedings.
Challenge
The UNCV workshop will run the BRAVO Challenge 2025, focusing on
stress-testing the reliability of semantic segmentation models under
realistic perturbations and unknown out-of-distribution (OOD)
scenarios. The BRAVO dataset is organized into six subsets, two with
real data and four based on the validation set of Cityscapes with
synthetic augmentations. It spans a range of corner-cases as follows:
adverse weather conditions, OOD objects, visibility impediments (rain
drops, flares), random backgrounds to assess spurious correlations.
More information about the MUAD dataset and its download link are
available at MUAD website.
Submission Instructions
At the time of submission authors must indicate the desired paper track:
Regular papers will be peer-reviewed following the same policy of
the main conference and will be published in the proceedings (call
for papers with guidelines and template here, max 8 pages,
additional pages for references only are allowed). These are meant
to present novel contributions not published previously (submitted
papers should not have been published, accepted or under review
elsewhere).
Extended abstracts are meant for preliminary works and short
versions of papers that have already been accepted, or are under
review, preferably in the last year in some major conferences or
journals. These papers will undergo a separate reviewing process
to assess the suitability for the workshop. These will *not
appear* in the workshop proceedings. Template and guidelines (max
4 content pages, additional pages for references allowed) here.
Submission site:
https://openreview.net/group?id=thecvf.com/CVPR/2025/Workshop/UnCV
Important Dates (All times are end of day AOE)
Submission deadline: Mar 14th, 2025
Notification of acceptance: April 1st, 2025
Camera-ready deadline: April 7th, 2025
Organizing Commitee
Andrea Pilzer, NVIDIA, Italy
Gianni Franchi, ENSTA Paris, France
Andrei Bursuc, valeo.ai, France
Arno Solin, Aalto University, Finland
Martin Trapp, Aalto University, Finland
Marcus Klasson, FCAI & Aalto University, Finland
Angela Yao, National University of Singapore, Singapore
Tuan-Hung Vu, valeo.ai and Inria, France
Fatma Güney, Koç University, Turkey