to
Drum Building, Madingley Rise, Madingley Road, Cambridge, CB3 0EZ and zoom.
About
On Tuesday 30 January our AI4ER seminar will be presented by Assoc Prof Sara Beery, Faculty of Artificial Intelligence and Decision-Making and CSAIL, MIT.
Talk title: Generalization vs Specialization in Computer Vision for Ecology
Abstract: There are explicit tradeoffs between generality and specificity in computer vision methods with respect to designing impactful end-to-end solutions for ecological challenges — computer vision systems that are general purpose but optimal for each stakeholder, taking into account cost, human effort, and risk. We explore these tradeoffs across several dimensions, investigating the impact of generality vs specificity with regards to data, labels, tasks, and models, and propose joint compression and specialization of large generalist models as an efficient and cost-effective alternative to retraining or fine tuning in resource-constrained scenarios such as remote field-based ecological monitoring.
Location: Drum Building, Madingley Rise, Madingley Road, Cambridge, CB3 0EZ and zoom.
For more info on future talks, or to view the archived records of past sessions, please visit the talks.cam page:
http://talks.cam.ac.uk/show/index/95728