Date:
Location:
Talk Title: Generalization vs Specialization in Computer Vision for Ecology
Talk 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.
Speaker: Dr. Sara Beery is an assistant professor in the MIT Faculty of Artificial Intelligence and Decision-Making. She was previously a visiting researcher at Google, working on large-scale urban forest monitoring as part of the Auto Arborist project. She received her PhD in Computing and Mathematical Sciences at Caltech in 2022, where she was advised by Pietro Perona and awarded the Amori Doctoral Prize for her thesis. Her research focuses on building computer vision methods that enable global-scale environmental and biodiversity monitoring across data modalities, tackling real-world challenges including geospatial and temporal domain shift, learning from imperfect data, fine-grained categories, and long-tailed distributions. She partners with industry, nongovernmental organizations, and government agencies to deploy her methods in the wild worldwide. She works toward increasing the diversity and accessibility of academic research in artificial intelligence through interdisciplinary capacity building and education, and has founded the AI for Conservation slack community, serves as the Biodiversity Community Lead for Climate Change AI, and founded and directs the Summer Workshop on Computer Vision Methods for Ecology.
If you would like to join our Seminar Series google group and receive a reminder about this event and upcoming seminars, please register here.