Objectives:
The aim of this course, together with its parallel subject Deep Learning for Visual Signal Processing II, is to help the student understand and apply the theoretical and practical fundamentals behind deep learning techniques applied to image analysis and synthesis. Specifically, this course covers: i) the different learning strategies mainly used in this domain (supervised, unsupervised, self-supervised, transfer learning and domain adaptation, continual and incremental learning, etc.), ii) advanced specific architectures for computer vision (graph visual networks, diffusion networks, etc.), iii) and the fundamental applications-techniques for image and video understanding (classification, segmentation, tracking, etc.).