Dr. Oisin Mac Aodha presents Learning from Visual Data in the Wild
On 2025-06-27 14:00:00 at G205, Karlovo náměstí 13, Praha 2
The wealth and complexity of visual information observable by artificial systems
deployed in the real world vastly exceeds the comparative simplicity of many of
our existing carefully curated computer vision benchmark datasets. To operate
safely and reliably in challenging environments, artificial systems need to be
able to recognize existing fine-grained visual concepts, discover new ones, and
to avail of the structure of the world around them. In this talk I will discuss
work from my group on problems related to learning from visual data “in the
wild”. Specifically, I will cover recent work spanning fine-grained image
understanding, concept discovery, and multi-modal learning.
deployed in the real world vastly exceeds the comparative simplicity of many of
our existing carefully curated computer vision benchmark datasets. To operate
safely and reliably in challenging environments, artificial systems need to be
able to recognize existing fine-grained visual concepts, discover new ones, and
to avail of the structure of the world around them. In this talk I will discuss
work from my group on problems related to learning from visual data “in the
wild”. Specifically, I will cover recent work spanning fine-grained image
understanding, concept discovery, and multi-modal learning.