2nd Workshop on Dealing with Novelty in Open Worlds: DNOW

Jan 3rd 2023, to be held in conjunction with WACV 2023

Overview

Visual perception is indispensable for numerous applications, spanning transportation, healthcare, security, commerce, entertainment, and interdisciplinary research. Currently, visual perception algorithms are often developed in a closed-world paradigm, in which the training data will likely not represent the entire open world. Algorithms developed in a closed world appear to be brittle once exposed to the open world, where they are unable to properly handle novel objects and scenarios. This workshop invites researchers to stimulate fruitful discussions to move forward computer vision research in open worlds.

Examples

Let's consider the following motivational examples:

• An autonomous vehicle may not recognize an overturned truck
• A visual recognition system used in entertainment might not fairly recognize people of different races
• A fashion recommendation system might not produce satisfactory recommendation results for "new-arrival" clothes.
• An e-commerce system might not check new-products that are posted in reviews or uploaded for sale.

Impact

Addressing novelties in open worlds have broad societal impacts. For example,

• It improves the safety and robustness of vision systems, e.g., flagging an alert when seeing an unknown object in autonomous driving
• It helps interdisciplinary research, e.g., discovering novel species of biological organisms
• It helps mitigate bias and promotes fairness in AI or machine learning applications, e.g., detecting and carefully handling underrepresented subpopulations rather than blindly making predictions about them.

Outcomes

We expect that our workshop will

• offer new insights to the audience with respect to new challenges and opportunities when studying computer vision systems in the open-world
• give voice to the need for more attention to open-world paradigms and will continue the discussion, from previous such workshops/seminars, on the formalization of metrics and datasets in this space
• provide a platform to exchange ideas among people that have different backgrounds and that come from different fields
• bridge the gaps of academic research experiments and the requirements of real-world applications
• explore mechanisms to measure competence at recognizing and dealing with novelty. This is especially important since the distribution of the test data (and presumably the evaluation date) will by definition, differ from the training data. This introduces challenges for evaluation as well as achieving competence.

Program Schedule

Organizers

Pulkit Kumar

University of Maryland

Anubhav

University of Maryland

Shu Kong

TAMU

Dawei Du

Kitware

Christopher Funk

Kitware

Walter Scheirer

University of Notre Dame

Terrance Boult

UCCS

Carl Vondrick

Columbia University

Abhinav Shrivastava

University of Maryland