Domain Adaptation in Computer Vision Applications

ISBN-13: 9783319583464 / Angielski / Twarda / 2017 / 344 str.

Gabriela Csurka

Opis

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.

Spis treści

1. A Comprehensive Survey on Domain Adaptation for Visual Applications
Gabriela Csurka

2. A Deeper Look at Dataset Bias
Tatiana Tommasi, Novi Patricia, Barbara Caputo, and Tinne Tuytelaars

Part I: Shallow Domain Adaptation Methods

3. Geodesic Flow Kernel and Landmarks: Kernel Methods for Unsupervised Domain Adaptation
Boqing Gong, Kristen Grauman, and Fei Sha

4. Unsupervised Domain Adaptation based on Subspace Alignment
Basura Fernando, Rahaf Aljundi, Rémi Emonet, Amaury Harbard, Marc Sebban, and Tinne Tuytelaars

5. Learning Domain Invariant Embeddings by Matching Distributions
Mahsa Baktashmotlagh, Mehrtash Harandi, and Mathieu Salzmann

6. Adaptive Transductive Transfer Machines: A Pipeline for Unsupervised Domain Adaptation
Nazli Farajidavar, Teofilo de Campos, and Josef Kittler

7. What To Do When the Access to the Source Data is Constrained?
Gabriela Csurka, Boris Chidlovskii, and Stéphane Clinchant

Part II: Deep Domain Adaptation Methods

8. Correlation Alignment for Unsupervised Domain Adaptation
Baochen Sun, Jiashi Feng, and Kate Saenko

9. Simultaneous Deep Transfer Across Domains and Tasks
Judy Hoffman, Eric Tzeng, Trevor Darrell, and Kate Saenko

10. Domain-Adversarial Training of Neural Networks
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky

Part III: Beyond Image Classification

11. Unsupervised Fisher Vector Adaptation for Re-Identification
Usman Tariq, Jose A. Rodriguez-Serrano, and Florent Perronnin

12. Semantic Segmentation of Urban Scenes via Domain Adaptation of SYNTHIA
German Ros, Laura Sellart, Gabriel Villalonga, Elias Maidanik, Francisco Molero, Marc Garcia, Adriana Cedeño, Francisco Perez, Didier Ramirez, Eduardo Escobar, Jose Luis Gomez, David Vazquez, and Antonio M. Lopez

13. From Virtual to Real World Visual Perception using Domain Adaptation – The DPM as Example
Antonio M. López, Jiaolong Xu, José L. Gómez, David Vázquez, and Germán Ros

14. Generalizing Semantic Part Detectors Across Domains
David Novotny, Diane Larlus, and Andrea Vedaldi

Part IV: Beyond Domain Adaptation: Unifying Perspectives

15. A Multi-Source Domain Generalization Approach to Visual Attribute Detection
Chuang Gan, Tianbao Yang, and Boqing Gong

16. Unifying Multi-Domain Multi-Task Learning: Tensor and Neural Network Perspectives
Yongxin Yang and Timothy M. Hospedales

O autorze

Dr. Gabriela Csurka is a Senior Scientist in the Computer Vision Team at Naver Labs Europe, Meylan, France.

Blurb

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.