Florent Perronnin is a Research Scientist Manager with Facebook AI Research, and Director of the Paris lab.
He received his Engineering degree from Télécom ParisTech in 2000 and his PhD in Computer Science from EPFL in 2004.
Prior to joining Facebook, Florent was a Principal Scientist and a Manager of the Computer Vision Group at Xerox Research in Grenoble.
There, he led several projects around visual recognition which won many awards in international benchmarks such as PASCAL VOC or ImageNet.
|Contributions to Fine-Grained Visual Categorisation||05 NOV 2015||02:00pm - 02:45pm|
While in the past the computer vision community focused on tasks considered trivial for humans, e.g. distinguishing cats from dogs, it has recently started focusing on tasks which are non-trivial even for humans, such as recognising breeds of cats or dogs. These are two examples of fine-grained recognition tasks, i.e. tasks which involve a large number of semantically related and visually similar classes. Other examples of fine-grained tasks include the recognition of plants and flora or the recognition of brands and models of cars. Fine-grained recognition comes with several challenges. This includes the fact that similar categories can be difficult to distinguish because they only defer by very subtle details. This also includes the paucity of labeled training data which stems from the fact that fine-grained annotations require expert knowledge. During this talk, I will present some of our contributions to these problems.