CRCS Seminar Series, Sara Beery Generalization vs Specialization in Computer Vision for Ecology

Описание к видео CRCS Seminar Series, Sara Beery Generalization vs Specialization in Computer Vision for Ecology

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.

Комментарии

Информация по комментариям в разработке

Похожие видео