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 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
Preface Emlyn Roy Davies, Octavia Camps and Matthew Turk 1. The changing face of computer vision Emlyn Roy Davies 2. Developments in machine learning: from deep networks to deep functional scene understanding Cornelia Fermüller 3. Adversarial examples in deep learning Andrea Cavallaro 4. Learning with reinforcement and limited supervision Amit Roy Chowdhury 5. Self-supervised event segmentation Sudeep Sarkar 6. Advanced methods for robust object detection Nuno Vasconcelos 7. Recognition and tracking in scenes containing multiple moving objects Michael Felsberg 8. Domain adaptation and incremental learning for semantic segmentation Pietro Zanuttigh 9. Methodologies for partial and complete face detection Hassan Ugail 10. Modern approaches to anomaly detection Carlo Regazzoni 11. Learning and reconstructing complex 3D objects from multiple views Gerard Pons-Moll 12. Dynamics-based invariants for video analytics Octavia Camps 13. State of the art on object re-identification Bastian Leibe 14. Principled methods for improving efficiency of deep neural networks Song Han 15. Methodology for long-term visual object tracking Efstratios Gavves 16. Conditional image generation for learning the structure of visual objects Gang Hua 17. Domain adaptive deep learning Rama Chellappa 18. Combining model-based and deep learned-based approaches for image restoration Radu Timofte