Deep Learning for Recognizing Species and Individuals

Abstract: Deep learning has enabled computers to "see" like humans across many domains. Initial successes were in object-level visual recognition, such as object recognition, detection, and instance-level segmentation. As people are generally the dominant subjects in most images, this has facilitated the collection of large datasets, and has led to breakthroughs in person-centric applications, such as face detection and recognition, re-identification, pose estimation, and activity recognition. Much less attention has been paid to the wider class of animals. Beyond people and inanimate objects, deep vision can play a role in our understanding of animal behaviour and social structure, from insects to mammals. In this talk, I will describe recent collaborations with biologists and environmental scientists that involve fine-grained vision, from the level of the species to the individual.

Biography: Graham Taylor is a Canada Research Chair and Associate Professor of Engineering at the University of Guelph. He directs the University of Guelph Centre for Advancing Responsible and Ethical AI and is a member of the Vector Institute for AI. He has co-organized the annual CIFAR Deep Learning Summer School, and trained more than 60 students and researchers on AI-related projects. In 2016 he was named as one of 18 inaugural CIFAR Azrieli Global Scholars. In 2018 he was honoured as one of Canada's Top 40 under 40. In 2019 he was named a Canada CIFAR AI Chair. He spent 2018-2019 as a Visiting Faculty member at Google Brain, Montreal. Graham co-founded Kindred, which was featured at number 29 on MIT Technology Review's 2017 list of smartest companies in the world. He is the Academic Director of NextAI, a non-profit accelerator for AI-focused entrepreneurs.

Monday March 30, 2020 at 1:30 PM in Arts 241

Doors Open at 1:15 PM