Domain Adaptation in Computer Vision Applications

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.

Table of Contents

Chapter 1 A Comprehensive Survey On Domain Adaptation For Visual Applications
Chapter 2 A Deeper Look At Dataset Bias
Part I Shallow Domain Adaptation Methods
Chapter 3 Geodesic Flow Kernel And Landmarks: Kernel Methods For Unsupervised Domain Adaptation
Chapter 4 Unsupervised Domain Adaptation Based On Subspace Alignment
Chapter 5 Learning Domain Invariant Embeddings By Matching Distributions
Chapter 6 Adaptive Transductive Transfer Machines: A Pipeline For Unsupervised Domain Adaptation
Chapter 7 What To Do When The Access To The Source Data Is Constrained?

Part II Deep Domain Adaptation Methods
Chapter 8 Correlation Alignment For Unsupervised Domain Adaptation
Chapter 9 Simultaneous Deep Transfer Across Domains And Tasks
Chapter 10 Domain-Adversarial Training Of Neural Networks

Part III Beyond Image Classification
Chapter 11 Unsupervised Fisher Vector Adaptation For Re-Identification
Chapter 12 Semantic Segmentation Of Urban Scenes Via Domain Adaptation Of Synthia
Chapter 13 From Virtual To Real World Visual Perception Using Domain Adaptation—The Dpm As Example
Chapter 14 Generalizing Semantic Part Detectors Across Domains

Part IV Beyond Domain Adaptation: Unifying Perspectives
Chapter 15 A Multisource Domain Generalization Approach To Visual Attribute Detection
Chapter 16 Unifying Multi-Domain Multitask Learning: Tensor And Neural Network Perspectives