Advanced Methods and Deep Learning in Computer Vision
- 1st Edition - November 9, 2021
- Imprint: Academic Press
- Editors: E. R. Davies, Matthew Turk
- Language: English
- Paperback ISBN:9 7 8 - 0 - 1 2 - 8 2 2 1 0 9 - 9
- eBook ISBN:9 7 8 - 0 - 1 2 - 8 2 2 1 4 9 - 5
Advanced Methods and Deep Learning in Computer Vision presents advanced computer vision methods, emphasizing machine and deep learning techniques that have emerged during the past… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteAdvanced Methods and Deep Learning in Computer Vision presents advanced computer vision methods, emphasizing machine and deep learning techniques that have emerged during the past 5–10 years. The book provides clear explanations of principles and algorithms supported with applications. Topics covered include machine learning, deep learning networks, generative adversarial networks, deep reinforcement learning, self-supervised learning, extraction of robust features, object detection, semantic segmentation, linguistic descriptions of images, visual search, visual tracking, 3D shape retrieval, image inpainting, novelty and anomaly detection.
This book provides easy learning for researchers and practitioners of advanced computer vision methods, but it is also suitable as a textbook for a second course on computer vision and deep learning for advanced undergraduates and graduate students.
- Provides an important reference on deep learning and advanced computer methods that was created by leaders in the field
- Illustrates principles with modern, real-world applications
- Suitable for self-learning or as a text for graduate courses
Researchers, industry practitioners, and graduate students in computer vision and medical imaging
- Cover image
- Title page
- Table of Contents
- Copyright
- Dedication
- List of contributors
- About the editors
- Preface
- Chapter 1: The dramatically changing face of computer vision
- Abstract
- Acknowledgements
- 1.1. Introduction – computer vision and its origins
- 1.2. Part A – Understanding low-level image processing operators
- 1.3. Part B – 2-D object location and recognition
- 1.4. Part C – 3-D object location and the importance of invariance
- 1.5. Part D – Tracking moving objects
- 1.6. Part E – Texture analysis
- 1.7. Part F – From artificial neural networks to deep learning methods
- 1.8. Part G – Summary
- References
- Chapter 2: Advanced methods for robust object detection
- Abstract
- 2.1. Introduction
- 2.2. Preliminaries
- 2.3. R-CNN
- 2.4. SPP-Net
- 2.5. Fast R-CNN
- 2.6. Faster R-CNN
- 2.7. Cascade R-CNN
- 2.8. Multiscale feature representation
- 2.9. YOLO
- 2.10. SSD
- 2.11. RetinaNet
- 2.12. Detection performances
- 2.13. Conclusion
- References
- Chapter 3: Learning with limited supervision
- Abstract
- Acknowledgements
- 3.1. Introduction
- 3.2. Context-aware active learning
- 3.3. Weakly supervised event localization
- 3.4. Domain adaptation of semantic segmentation using weak labels
- 3.5. Weakly-supervised reinforcement learning for dynamical tasks
- 3.6. Conclusions
- References
- Chapter 4: Efficient methods for deep learning
- Abstract
- 4.1. Model compression
- 4.2. Efficient neural network architectures
- 4.3. Conclusion
- References
- Chapter 5: Deep conditional image generation
- Abstract
- 5.1. Introduction
- 5.2. Visual pattern learning: a brief review
- 5.3. Classical generative models
- 5.4. Deep generative models
- 5.5. Deep conditional image generation
- 5.6. Disentanglement for controllable synthesis
- 5.7. Conclusion and discussions
- References
- Chapter 6: Deep face recognition using full and partial face images
- Abstract
- 6.1. Introduction
- 6.2. Components of deep face recognition
- 6.3. Face recognition using full face images
- 6.4. Deep face recognition using partial face data
- 6.5. Specific model training for full and partial faces
- 6.6. Discussion and conclusions
- References
- Chapter 7: Unsupervised domain adaptation using shallow and deep representations
- Abstract
- 7.1. Introduction
- 7.2. Unsupervised domain adaptation using manifolds
- 7.3. Unsupervised domain adaptation using dictionaries
- 7.4. Unsupervised domain adaptation using deep networks
- 7.5. Summary
- References
- Chapter 8: Domain adaptation and continual learning in semantic segmentation
- Abstract
- Acknowledgement
- 8.1. Introduction
- 8.2. Unsupervised domain adaptation
- 8.3. Continual learning
- 8.4. Conclusion
- References
- Chapter 9: Visual tracking
- Abstract
- Acknowledgement
- 9.1. Introduction
- 9.2. Template-based methods
- 9.3. Online-learning-based methods
- 9.4. Deep learning-based methods
- 9.5. The transition from tracking to segmentation
- 9.6. Conclusions
- References
- Chapter 10: Long-term deep object tracking
- Abstract
- 10.1. Introduction
- 10.2. Short-term visual object tracking
- 10.3. Long-term visual object tracking
- 10.4. Discussion
- References
- Chapter 11: Learning for action-based scene understanding
- Abstract
- Acknowledgement
- 11.1. Introduction
- 11.2. Affordances of objects
- 11.3. Functional parsing of manipulation actions
- 11.4. Functional scene understanding through deep learning with language and vision
- 11.5. Future directions
- 11.6. Conclusions
- References
- Chapter 12: Self-supervised temporal event segmentation inspired by cognitive theories
- Abstract
- Acknowledgements
- 12.1. Introduction
- 12.2. The event segmentation theory from cognitive science
- 12.3. Version 1: single-pass temporal segmentation using prediction
- 12.4. Version 2: segmentation using attention-based event models
- 12.5. Version 3: spatio-temporal localization using prediction loss map
- 12.6. Other event segmentation approaches in computer vision
- 12.7. Conclusions
- References
- Chapter 13: Probabilistic anomaly detection methods using learned models from time-series data for multimedia self-aware systems
- Abstract
- 13.1. Introduction
- 13.2. Base concepts and state of the art
- 13.3. Framework for computing anomaly in self-aware systems
- 13.4. Case study results: anomaly detection on multisensory data from a self-aware vehicle
- 13.5. Conclusions
- References
- Chapter 14: Deep plug-and-play and deep unfolding methods for image restoration
- Abstract
- Acknowledgements
- 14.1. Introduction
- 14.2. Half quadratic splitting (HQS) algorithm
- 14.3. Deep plug-and-play image restoration
- 14.4. Deep unfolding image restoration
- 14.5. Experiments
- 14.6. Discussion and conclusions
- References
- Chapter 15: Visual adversarial attacks and defenses
- Abstract
- Acknowledgement
- 15.1. Introduction
- 15.2. Problem definition
- 15.3. Properties of an adversarial attack
- 15.4. Types of perturbations
- 15.5. Attack scenarios
- 15.6. Image processing
- 15.7. Image classification
- 15.8. Semantic segmentation and object detection
- 15.9. Object tracking
- 15.10. Video classification
- 15.11. Defenses against adversarial attacks
- 15.12. Conclusions
- References
- Index
- Edition: 1
- Published: November 9, 2021
- Imprint: Academic Press
- No. of pages: 582
- Language: English
- Paperback ISBN: 9780128221099
- eBook ISBN: 9780128221495
ED
E. R. Davies
Roy Davies was Emeritus Professor of Machine Vision at Royal Holloway, University of London. He worked on many aspects of vision, from feature detection to robust, real-time implementations of practical vision tasks. His interests included automated visual inspection, surveillance, vehicle guidance, crime detection and neural networks. He has published more than 200 papers, and three books. Machine Vision: Theory, Algorithms, Practicalities (1990) has been widely used internationally for more than 25 years, and is now out in this much enhanced fifth edition. Roy held a DSc at the University of London and was awarded Distinguished Fellow of the British Machine Vision Association, and Fellow of the International Association of Pattern Recognition.
Affiliations and expertise
Emeritus Professor of Machine Vision, Royal Holloway, University of London, UK (deceased)MT
Matthew Turk
Matthew Turk is a professor and department chair of the Department of Computer Science at the University of California, Santa Barbara, California. He was named a Fellow of the Institute of Electrical and Electronics Engineers (IEEE) in 2013[1] for his contributions to computer vision and perceptual interfaces. Starting on July 1st, he will be the president of the Toyota Technological Institute at Chicago[2]. In 2014, Turk was named a Fellow of the International Association for Pattern Recognition (IAPR)[3] for his contributions to computer vision and vision based interaction.
Affiliations and expertise
Professor and Department Chair, Department of Computer Science, University of California, Santa Barbara, CA, USARead Advanced Methods and Deep Learning in Computer Vision on ScienceDirect