© 2018

Explainable and Interpretable Models in Computer Vision and Machine Learning

  • Hugo Jair Escalante
  • Sergio Escalera
  • Isabelle Guyon
  • Xavier Baró
  • Yağmur Güçlütürk
  • Umut Güçlü
  • Marcel  van Gerven

Table of contents

  1. Front Matter
    Pages i-xvii
  2. Notions and Concepts on Explainability and Interpretability

    1. Front Matter
      Pages 1-1
    2. Gabriëlle Ras, Marcel van Gerven, Pim Haselager
      Pages 19-36
  3. Explainability and Interpretability in Machine Learning

    1. Front Matter
      Pages 37-37
    2. Olivier Goudet, Diviyan Kalainathan, Philippe Caillou, Isabelle Guyon, David Lopez-Paz, Michèle Sebag
      Pages 39-80
    3. Eneldo Loza Mencía, Johannes Fürnkranz, Eyke Hüllermeier, Michael Rapp
      Pages 81-113
    4. Laura Rieger, Pattarawat Chormai, Grégoire Montavon, Lars Kai Hansen, Klaus-Robert Müller
      Pages 115-131
  4. Explainability and Interpretability in Computer Vision

    1. Front Matter
      Pages 133-133
    2. Zeynep Akata, Lisa Anne Hendricks, Stephan Alaniz, Trevor Darrell
      Pages 135-154
    3. Nazneen Fatema Rajani, Raymond J. Mooney
      Pages 155-172
    4. Jinkyu Kim, John Canny
      Pages 173-193
  5. Explainability and Interpretability in First Impressions Analysis

    1. Front Matter
      Pages 195-195
    2. Cynthia C. S. Liem, Markus Langer, Andrew Demetriou, Annemarie M. F. Hiemstra, Achmadnoer Sukma Wicaksana, Marise Ph. Born et al.
      Pages 197-253
    3. Sathyanarayanan N. Aakur, Fillipe D. M. de Souza, Sudeep Sarkar
      Pages 277-299

About this book


This book compiles leading research on the development of explainable and interpretable machine learning methods in the context of computer vision and machine learning.

Research progress in computer vision and pattern recognition has led to a variety of modeling techniques with almost human-like performance. Although these models have obtained astounding results, they are limited in their explainability and interpretability: what is the rationale behind the decision made? what in the model structure explains its functioning? Hence, while good performance is a critical required characteristic for learning machines, explainability and interpretability capabilities are needed to take learning machines to the next step to include them in decision support systems involving human supervision.   

 This book, written by leading international researchers, addresses key topics of explainability and interpretability, including the following:


·         Evaluation and Generalization in Interpretable Machine Learning

·         Explanation Methods in Deep Learning

·         Learning Functional Causal Models with Generative Neural Networks

·         Learning Interpreatable Rules for Multi-Label Classification

·         Structuring Neural Networks for More Explainable Predictions

·         Generating Post Hoc Rationales of Deep Visual Classification Decisions

·         Ensembling Visual Explanations

·         Explainable Deep Driving by Visualizing Causal Attention

·         Interdisciplinary Perspective on Algorithmic Job Candidate Search

·         Multimodal Personality Trait Analysis for Explainable Modeling of Job Interview Decisions

·         Inherent Explainability Pattern Theory-based Video Event Interpretations


Explainable models in computer vision Explainable learning machines Interpretable models Explaining human behavior from data Interpreting human behavior analysis models Explaining first impressions Job candidate screening Multimodal analysis of human behavior Explaining Looking at people Chalearn looking at people challenges Explainable and interpretable decision support systems Benchmarking of explainable and interpretable models

Editors and affiliations

  • Hugo Jair Escalante
    • 1
  • Sergio Escalera
    • 2
  • Isabelle Guyon
    • 3
  • Xavier Baró
    • 4
  • Yağmur Güçlütürk
    • 5
  • Umut Güçlü
    • 6
  • Marcel  van Gerven
    • 7
  1. 1.INAOEPueblaMexico
  2. 2.University of BarcelonaBarcelonaSpain
  3. 3.INRIA, Université Paris Sud, Université Paris SaclayParisFrance
  4. 4.Open University of CataloniaBarcelonaSpain
  5. 5.Radboud University NijmegenNijmegenThe Netherlands
  6. 6.Radboud University NijmegenNijmegenThe Netherlands
  7. 7.Radboud University NijmegenNijmegenThe Netherlands

Bibliographic information

  • Book Title Explainable and Interpretable Models in Computer Vision and Machine Learning
  • Editors Hugo Jair Escalante
    Sergio Escalera
    Isabelle Guyon
    Xavier Baró
    Yağmur Güçlütürk
    Umut Güçlü
    Marcel van Gerven
  • Series Title The Springer Series on Challenges in Machine Learning
  • Series Abbreviated Title The Springer Series on Challenges in Machine Learning
  • DOI
  • Copyright Information Springer Nature Switzerland AG 2018
  • Publisher Name Springer, Cham
  • eBook Packages Computer Science Computer Science (R0)
  • Hardcover ISBN 978-3-319-98130-7
  • eBook ISBN 978-3-319-98131-4
  • Series ISSN 2520-131X
  • Series E-ISSN 2520-1328
  • Edition Number 1
  • Number of Pages XVII, 299
  • Number of Illustrations 15 b/w illustrations, 58 illustrations in colour
  • Topics Artificial Intelligence
    Image Processing and Computer Vision
    Pattern Recognition
  • Buy this book on publisher's site