News

Seminario: “Getting more for less out of your Convolutional Neural Networks”

Lunedì 21 Maggio 2018, ore 15:00 - Aula 1AD100 - Andrew D. Bagdanov

ARGOMENTI: Seminari

Lunedì 21 Maggio 2018 alle ore 15:00 in Aula 1AD100, Andrew D. Bagdanov (University of Florence) terrà un seminario dal titolo “Getting more for less out of your Convolutional Neural Networks”.

Abstract
Computer vision has been undergoing a major transformation over the past five years. The advent of viable, deep neural network architectures for visual recognition continues to radically change the landscape of the state-of-the-art in computer vision across the board. These developments have brought amazing new possibilities and formidable new challenges to the table. In this one-hour seminar I will talk about two recent lines of research addressing problems with the long-term sustainability of Convolutional Neural Networks (CNNs) for visual recognition problems: i) self-supervised learning, ii) deep network compression. These lines of research directly address critical issues in training and deployment of state-of-the-art CNNs and enable one to get more from CNNs for less — that is, to obtain state-of-the-art results on multiple visual recognition tasks with fewer labeled training examples and smaller memory footprint.

Short Bio
Andrew D. Bagdanov received a PhD in computer science from the University of Amsterdam in 2004. He held postdoctoral positions at the University of Florence and Universitat Autònoma de Barcelona. He was Senior Development Chief at the FAO of the United Nations, Head of Research Unit at the Media Integration and Communication Center, and Ramon y Cajal Fellow at the Computer Vision Center, Barcelona. Since 2016, Andrew is Associate Professor in the Information Engineering department at the Università degli Studi di Firenze. His research spans a broad spectrum of computer vision, image processing and machine learning. He has held senior professional and academic positions in four countries, and has published over ninety scientific articles in peer-reviewed, international journals and conference proceedings.