Less-Supervised Segmentation with CNNs
Scenarios, Models and Optimization
- 1st Edition - December 1, 2024
- Editors: Jose Dolz, Ismail Ben Ayed, Christian Desrosiers
- Language: English
- Paperback ISBN:9 7 8 - 0 - 3 2 3 - 9 5 6 7 4 - 1
- eBook ISBN:9 7 8 - 0 - 3 2 3 - 9 5 6 7 5 - 8
Less-Supervised Segmentation with CNNs: Scenarios, Models and Optimization reviews recent progress in deep learning for image segmentation under scenarios with limited supervisi… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteLess-Supervised Segmentation with CNNs: Scenarios, Models and Optimization reviews recent progress in deep learning for image segmentation under scenarios with limited supervision, with a focus on medical imaging. The book presents main approaches and state-of-the-art models and includes a broad array of applications in medical image segmentation, including healthcare, oncology, cardiology and neuroimaging. A key objective is to make this mathematical subject accessible to a broad engineering and computing audience by using a large number of intuitive graphical illustrations. The emphasis is on giving conceptual understanding of the methods to foster easier learning.
This book is highly suitable for researchers and graduate students in computer vision, machine learning and medical imaging.
- Presents a good understanding of the different weak-supervision models (i.e., loss functions and priors) and the conceptual connections between them, providing an ability to choose the most appropriate model for a given application scenario
- Provides knowledge of several possible optimization strategies for each of the examined losses, giving the ability to choose the most appropriate optimizer for a given problem or application scenario
- Outlines the main strengths and weaknesses of state-of-the-art approaches
- Gives the tools to understand and use publicly-available code, as well as customize it for specific objectives
Researchers and graduate students in medical imaging, computer vision, machine learning
1. Introduction
2. Preliminaries
3. Different levels of supervision Different supervisions Priors a Knowledge driven priorsIII Data driven priors A unified view
4. Semi-supervised learning Introduction to the setting Adversarial learning Consistency regularization Unsupervised representation learning Self-paced learning Mixed-supervision
5. Unsupervised domain adaptation Introduction to the setting Adversarial learning Source-free adaptation Domain generalization?
6. Weakly supervised segmentation Introduction to the setting From global cues to pixel labels Constrained CNNs Equality constraints Constrained CNNs: Inequality constraints Class activation maps based methods
7. Few-shot learning Introduction to the setting Learning to learn Data augmentation Simple baselines Invited
8. Unsupervised segmentation Introduction to the setting Auto-encoders Use of the gradient Leveraging constraints
9. Perspectives and future directions
2. Preliminaries
3. Different levels of supervision Different supervisions Priors a Knowledge driven priorsIII Data driven priors A unified view
4. Semi-supervised learning Introduction to the setting Adversarial learning Consistency regularization Unsupervised representation learning Self-paced learning Mixed-supervision
5. Unsupervised domain adaptation Introduction to the setting Adversarial learning Source-free adaptation Domain generalization?
6. Weakly supervised segmentation Introduction to the setting From global cues to pixel labels Constrained CNNs Equality constraints Constrained CNNs: Inequality constraints Class activation maps based methods
7. Few-shot learning Introduction to the setting Learning to learn Data augmentation Simple baselines Invited
8. Unsupervised segmentation Introduction to the setting Auto-encoders Use of the gradient Leveraging constraints
9. Perspectives and future directions
- No. of pages: 275
- Language: English
- Edition: 1
- Published: December 1, 2024
- Imprint: Academic Press
- Paperback ISBN: 9780323956741
JD
Jose Dolz
Jose Dolz is an Associate Professor in the Department of Software and IT Engineering at the ETS Montreal. Prior to be appointed Professor, he was a post-doctoral fellow at the ETS Montreal. Dr. Dolz obtained his B.Sc and M.Sc in the Polytechnic University of Valencia, Spain, and his Ph.D. at the University of Lille 2, France, in 2016. Dr. Dolz was recipient of a Marie-Curie FP7 Fellowship (2013-2016) to pursue his doctoral studies. His current research focuses on deep learning, medical imaging, optimization and learning strategies with limited supervision. He authored over 30 fully peer-reviewed papers, many of which published in the top venues in medical imaging (MICCAI/IPMI/MedIA/TMI/NeuroImage), vision (CVPR) and machine learning (ICML, NeurIPS).
Affiliations and expertise
Associate Professor, Department of Software and IT Engineering, ETS Montreal, CanadaIB
Ismail Ben Ayed
Ismail Ben Ayed received a Ph.D. degree (with the highest honor) in the area of computer vision from the National Institute of Scientific Research (INRS-EMT), University of Quebec, Montreal, QC, Canada, in May 2007, under the guidance of Professor Amar Mitiche. Since then, he has been a research scientist with GE Healthcare, London, ON, Canada, conducting research in medical image analysis. He also holds an Adjunct Professor appointment at Western University, department of Medical Biophysics. He co-authored a book, over 50 peer-reviewed papers in reputable journals and conferences, and six patents. He received a GE recognition award in 2012 and a GE innovation award in 2010
Ismail Ben Ayed is an image segmentation and optimization expert who has authored over 60 peer-reviewed articles in the field and has co-authored the book Variational and Level Set Methods in Image Segmentation, 2011, which is receiving a high citation rate.
Affiliations and expertise
Professor, Departement de Genie de la Production Automatisee, ETS, Montreal, CanadaCD
Christian Desrosiers
Christian Desrosiers,
Since 2009 Christian Desrosiers has worked as an assistant professor in the Software and IT Engineering department at ÉTS, Montreal. Before joining the department, he was a postdoctoral research assistant at the University of Minnesota, under the supervision of professor George Karypis. He obtained my Ph.D. in applied mathematics at École Polytechnique de Montréal, in 2008.
His main areas of research are data mining, machine learning, biomedical imaging, recommender systems and business intelligence.
Affiliations and expertise
Assistant Professor, Software and IT Engineering Department, ETS, Montreal, Canada