Domain Adaptation in Computer Vision Applications

  • Gabriela Csurka

Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Table of contents

  1. Front Matter
    Pages i-x
  2. Tatiana Tommasi, Novi Patricia, Barbara Caputo, Tinne Tuytelaars
    Pages 37-55
  3. Shallow Domain Adaptation Methods

    1. Front Matter
      Pages 57-57
    2. Basura Fernando, Rahaf Aljundi, Rémi Emonet, Amaury Habrard, Marc Sebban, Tinne Tuytelaars
      Pages 81-94
    3. Mahsa Baktashmotlagh, Mehrtash Harandi, Mathieu Salzmann
      Pages 95-114
    4. Nazli Farajidavar, Teofilo de Campos, Josef Kittler
      Pages 115-132
    5. Gabriela Csurka, Boris Chidlovskii, Stéphane Clinchant
      Pages 133-149
  4. Deep Domain Adaptation Methods

    1. Front Matter
      Pages 151-151
    2. Baochen Sun, Jiashi Feng, Kate Saenko
      Pages 153-171
    3. Judy Hoffman, Eric Tzeng, Trevor Darrell, Kate Saenko
      Pages 173-187
    4. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette et al.
      Pages 189-209
  5. Beyond Image Classification

    1. Front Matter
      Pages 211-211
    2. Usman Tariq, Jose A. Rodriguez-Serrano, Florent Perronnin
      Pages 213-225
    3. German Ros, Laura Sellart, Gabriel Villalonga, Elias Maidanik, Francisco Molero, Marc Garcia et al.
      Pages 227-241
    4. Antonio M. López, Jiaolong Xu, José L. Gómez, David Vázquez, Germán Ros
      Pages 243-258
    5. David Novotny, Diane Larlus, Andrea Vedaldi
      Pages 259-273
  6. Beyond Domain Adaptation: Unifying Perspectives

    1. Front Matter
      Pages 275-275
    2. Chuang Gan, Tianbao Yang, Boqing Gong
      Pages 277-289

About this book

Introduction

This comprehensive text/reference presents a broad review of diverse domain adaptation (DA) methods for machine learning, with a focus on solutions for visual applications. The book collects together solutions and perspectives proposed by an international selection of pre-eminent experts in the field, addressing not only classical image categorization, but also other computer vision tasks such as detection, segmentation and visual attributes.

Topics and features:

  • Surveys the complete field of visual DA, including shallow methods designed for homogeneous and heterogeneous data as well as deep architectures
  • Presents a positioning of the dataset bias in the CNN-based feature arena
  • Proposes detailed analyses of popular shallow methods that addresses landmark data selection, kernel embedding, feature alignment, joint feature transformation and classifier adaptation, or the case of limited access to the source data
  • Discusses more recent deep DA methods, including discrepancy-based adaptation networks and adversarial discriminative DA models
  • Addresses domain adaptation problems beyond image categorization, such as a Fisher encoding adaptation for vehicle re-identification, semantic segmentation and detection trained on synthetic images, and domain generalization for semantic part detection
  • Describes a multi-source domain generalization technique for visual attributes and a unifying framework for multi-domain and multi-task learning

This authoritative volume will be of great interest to a broad audience ranging from researchers and practitioners, to students involved in computer vision, pattern recognition and machine learning.

Dr. Gabriela Csurka is a Senior Scientist in the Computer Vision Team at Xerox Research Centre Europe, Meylan, France.

Keywords

Computer Vision Visual Applications Image Categorization Pattern Recognition Data Analytics Unsupervised Domain Adaptation Transductive Transfer Learning Domain Shift Feature Transformation Subspace Learning Landmark Selection Maximum Mean Discrepancy Grassman Manifold Geodesic Flow Subspace Alignment Marginalized Denoising Autoencoders Deep Learning Domain-Adversarial Training

Editors and affiliations

  • Gabriela Csurka
    • 1
  1. 1.Naver Labs EuropeMeylanFrance

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-319-58347-1
  • Copyright Information Springer International Publishing AG 2017
  • Publisher Name Springer, Cham
  • eBook Packages Computer Science
  • Print ISBN 978-3-319-58346-4
  • Online ISBN 978-3-319-58347-1
  • Series Print ISSN 2191-6586
  • Series Online ISSN 2191-6594
  • About this book