A new approach called open ad-hoc categorization (OAK) helps AI systems dynamically reinterpret the same image differently depending on the categorization context, rather than using fixed visual interpretation. A University of Michigan-led study on this topic was presented in June 2025 at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in Nashville, Tennessee.
AI system discovers visual categories while adapting to new contexts
Reader’s Picks
-
The global distribution of wealth is currently the subject of controversial debate. Against this backdrop, social sciences, humanities, and economics [...]
-
Teenagers can seem to have their phones glued to their hands—yet they won’t answer them when they ring. This scenario, [...]
-
As artificial intelligence (AI) tools like ChatGPT become part of our everyday lives, from providing general information to helping with [...]