Unsupervised Learning in Space and Time : A Modern Approach for Computer Vision using Graph-based Techniques and Deep Neural Networks / by Marius Leordeanu.

Format:

Book

Author/Creator:

Leordeanu, Marius, author.

Contributor:

SpringerLink (Online service)

Series:

Computer Science (SpringerNature-11645)

Advances in computer vision and pattern recognition 2191-6586

Advances in Computer Vision and Pattern Recognition, 2191-6586

Language:

English

Subjects (All):

Optical data processing.

Machine learning.

Computer science--Mathematics.

Computer science.

Image Processing and Computer Vision.

Machine Learning.

Mathematical Applications in Computer Science.

Local Subjects:

Image Processing and Computer Vision.

Machine Learning.

Mathematical Applications in Computer Science.

Physical Description:

1 online resource (XXIII, 298 pages) : 232 illustrations, 96 illustrations in color.

Edition:

First edition 2020.

Contained In:

Springer Nature eBook

Place of Publication:

Cham : Springer International Publishing : Imprint: Springer, 2020.

System Details:

text file PDF

Summary:

This book addresses one of the most important unsolved problems in artificial intelligence: the task of learning, in an unsupervised manner, from massive quantities of spatiotemporal visual data that are available at low cost. The book covers important scientific discoveries and findings, with a focus on the latest advances in the field. Presenting a coherent structure, the book logically connects novel mathematical formulations and efficient computational solutions for a range of unsupervised learning tasks, including visual feature matching, learning and classification, object discovery, and semantic segmentation in video. The final part of the book proposes a general strategy for visual learning over several generations of student-teacher neural networks, along with a unique view on the future of unsupervised learning in real-world contexts. Offering a fresh approach to this difficult problem, several efficient, state-of-the-art unsupervised learning algorithms are reviewed in detail, complete with an analysis of their performance on various tasks, datasets, and experimental setups. By highlighting the interconnections between these methods, many seemingly diverse problems are elegantly brought together in a unified way. Serving as an invaluable guide to the computational tools and algorithms required to tackle the exciting challenges in the field, this book is a must-read for graduate students seeking a greater understanding of unsupervised learning, as well as researchers in computer vision, machine learning, robotics, and related disciplines. Dr. Marius Leordeanu is an Associate Professor (Senior Lecturer) at the Computer Science and Engineering Department, Polytechnic University of Bucharest and a Senior Researcher at the Institute of Mathematics of the Romanian Academy (IMAR), Bucharest, Romania. In 2014, he was awarded the Grigore Moisil Prize, the most prestigious award in mathematics bestowed by the Romanian Academy, for his work on unsupervised learning.

Contents:

1. Unsupervised Visual Learning: from Pixels to Seeing

2. Unsupervised Learning of Graph and Hypergraph Matching

3. Unsupervised Learning of Graph and Hypergraph Clustering

4. Feature Selection meets Unsupervised Learning

5. Unsupervised Learning of Object Segmentation in Video with Highly Probable Positive Features

6. Coupling Appearance and Motion: Unsupervised Clustering for Object Segmentation through Space and Time

7. Unsupervised Learning in Space and Time over Several Generations of Teacher and Student Networks

8. Unsupervised Learning Towards the Future.

Other Format:

Printed edition:

ISBN:

978-3-030-42128-1

9783030421281

Access Restriction:

Restricted for use by site license.