Machine Learning with Noisy Labels

Machine Learning with Noisy Labels

by Gustavo Carneiro
Released February 2024
Publisher(s): Academic Press
ISBN: 9780443154423

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Most of the modern machine learning models, based on deep learning techniques, depend on carefully curated and cleanly labelled training sets to be reliably trained and deployed. However, the expensive labelling process involved in the acquisition of such training sets limits the number and size of datasets available to build new models, slowing down progress in the field. Alternatively, many poorly curated training sets containing noisy labels are readily available to be used to build new models. However, the successful exploration of such noisy-label training sets depends on the development of algorithms and models that are robust to these noisy labels.

Machine learning and Noisy Labels: Definitions, Theory, Techniques and Solutions defines different types of label noise, introduces the theory behind the problem, presents the main techniques that enable the effective use of noisy-label training sets, and explains the most accurate methods developed in the field.

This book is an ideal introduction to machine learning with noisy labels suitable for senior undergraduates, post graduate students, researchers and practitioners using, and researching into, machine learning methods.
  • Shows how to design and reproduce regression, classification and segmentation models using large-scale noisy-label training sets
  • Gives an understanding of the theory of, and motivation for, noisy-label learning
  • Shows how to classify noisy-label learning methods into a set of core techniques

Table of contents

  1. Cover image
  2. Title page
  3. Table of Contents
  4. Copyright
  5. Dedication
  6. Biography
    1. Gustavo Carneiro
  7. Preface
    1. Survey papers and books on the same topic
    2. Book organization
    3. Bibliography
  8. Acknowledgments
  9. Mathematical notation
  10. Chapter 1: Problem definition
    1. Abstract
    2. 1.1. Motivation
    3. 1.2. Introduction
    4. 1.3. Challenges
    5. 1.4. Conclusion
    6. Bibliography
  11. Chapter 2: Noisy-label problems and datasets
    1. Abstract
    2. 2.1. Introduction
    3. 2.2. Regression, classification, segmentation, and detection problems
    4. 2.3. Label noise problems
    5. 2.4. Closed set label noise problems
    6. 2.5. Open-set label noise problems
    7. 2.6. Label noise problem setup
    8. 2.7. Datasets and benchmarks
    9. 2.8. Evaluation
    10. 2.9. Conclusion
    11. Bibliography
  12. Chapter 3: Theoretical aspects of noisy-label learning
    1. Abstract
    2. 3.1. Introduction
    3. 3.2. Bias variance decomposition
    4. 3.3. The identifiability of the label transition distribution
    5. 3.4. PAC learning and noisy-label learning
    6. 3.5. Conclusion
    7. Bibliography
  13. Chapter 4: Noisy-label learning techniques
    1. Abstract
    2. 4.1. Introduction
    3. 4.2. Loss function
    4. 4.3. Data processing
    5. 4.4. Training algorithms
    6. 4.5. Model architecture
    7. 4.6. Conclusions
    8. Bibliography
  14. Chapter 5: Benchmarks, methods, results, and code
    1. Abstract
    2. 5.1. Introduction
    3. 5.2. Closed set label noise problems
    4. 5.3. Open set label noise problems
    5. 5.4. Imbalanced noisy-label problems
    6. 5.5. Noisy multi-label learning
    7. 5.6. Noisy-label segmentation problems
    8. 5.7. Noisy-label detection problems
    9. 5.8. Noisy-label medical image segmentation problems
    10. 5.9. Non-image noisy-label problems
    11. 5.10. Conclusion
    12. Bibliography
  15. Chapter 6: Conclusions and final considerations
    1. Abstract
    2. 6.1. Conclusions
    3. 6.2. Final considerations and future work
    4. Bibliography
  16. Bibliography
    1. Bibliography
  17. Index

Product information

  • Title: Machine Learning with Noisy Labels
  • Author(s): Gustavo Carneiro
  • Release date: February 2024
  • Publisher(s): Academic Press
  • ISBN: 9780443154423