Unsupervised Visual Learning: From Pixels to Seeing

• Published in: Unsupervised Learning in Space and Time pp. 1 - 52
• Main Author: Leordeanu, Marius
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer 2020; Springer International Publishing AG; Springer International Publishing
• Series: Advances in Computer Vision and Pattern Recognition
• ISBN: 3030421279; 9783030421274
• ISSN: 2191-6586; 2191-6594
• DOI: 10.1007/978-3-030-42128-1_1

This book is about unsupervised learningUnsupervised learning. That is one of the most challenging puzzles that we must solve and put together, piece by piece, in order to decode the secrets of intelligence. Here, we move closer to that goal by connecting classical computational models to newer deep learningDeep learning ones, and then build based on some fundamental and intuitive unsupervised learning principlesPrinciples of unsupervised learning. We want to reduce the unsupervised learningUnsupervised learning problem to a set of essential ideas and then develop the computational tools needed to implement them in the real world. Eventually, we aim to imagine a universal unsupervised learning machineUniversal unsupervised learning machine, the Visual Story NetworkVisual Story Network (VSN). The book is written for young students as well as experienced researchers, engineers, and professors. It presents computational models and optimization algorithms in sufficient technical detail, while also creating and maintaining a big intuitive picture about the main subject. Different tasks, such as graph matchingGraph matching and clustering, feature selection, classifier learning, unsupervised object discoveryUnsupervised object discovery and segmentation in video, teacher-studentTeacher-student unsupervised learning system learning over multiple generations as well as recursive graph neural networks are brought together, chapter by chapter, under the same umbrella of unsupervised learningUnsupervised learning. In the current chapter, we introduce the reader to the overall story of the book, which presents a unified image of the different topics that will be presented in detail in the chapters to follow. Besides sharing that main goal of learning without human supervision, the problems and tasks presented in the book also share common computational graph models and optimization methods, such as spectral graph matchingSpectral graph matching, spectral clustering, and the integer projected fixed point methodInteger Projected Fixed Point (IPFP) method. By bringing together similar mathematical formulations across different tasks, all guided by common intuitive principles towards a universal unsupervised learningUnsupervised learning system, the book invites the reader to absorb and then participate in the creation of the next generation of artificial intelligence.