NEW: Deep Learning for Color
Instructors: Simone Bianco and Marco Buzzelli, University of Milano-Bicocca
Level: Introductory
Duration: 2 Hours
Course Time: 
     New York: 20 October 2021, 10:00 - 12:15
     Paris: 20 October 2021, 16:00 - 08:15
     Tokyo: 20 October 2021, 23:00 - 21 October 01:15

Course Prerequisites: Basic knowledge of deep learning and basic knowledge of image processing.
Benefits:
Attendees will be able to:

• Understand the popular building blocks of deep networks.
• Understand the training process of deep networks.
• Have a clear view of the most noticeable color-related papers exploiting deep networks.

Course Description
The aim of this course is to give learners a basic understanding of modern neural networks and their use in color applications. The course begins with a recap of linear models and discussion of the stochastic optimization methods that are at the basis of the training of deep neural networks. The course then moves to an introduction of the popular building blocks of discriminative and generative neural networks.

The second part of the course introduces the most noticeable examples of the application of deep learning in several color-related research fields, such as color constancy, image restoration, image quality, and image super-resolution.

Intended Audience: scientists, engineers, students, and those wishing to have an understanding of modern neural networks and a view of the milestone papers in color-related research fields.

Simone Bianco obtained a PhD in computer science at DISCo (Dipartimento di Informatica, Sistemistica e Comunicazione) of the University of Milano-Bicocca, Italy (2010). He obtained a BSc and MSc in mathematics from the University of Milano-Bicocca, Italy, (2003 and 2006, respectively). He is currently an associate professor and his research interests include computer vision, machine learning, optimization algorithms, and color imaging.

Marco Buzzelli obtained his bachelor and master in computer science (2012 and 2014, respectively), focusing on image processing and computer vision tasks. He received his PhD in computer science (2019) at the University of Milano-Bicocca (Italy), where he is currently employed as a post-doctoral researcher. His main topics of research include characterization of digital imaging devices and object recognition in complex scenes.

For office use only: