Domain adaptation in computer vision applications

Description

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. Front Matter ....Pages i-x A Comprehensive Survey on Domain Adaptation for Visual Applications (Gabriela Csurka)....Pages 1-35 A Deeper Look at Dataset Bias (Tatiana Tommasi, Novi Patricia, Barbara Caputo, Tinne Tuytelaars)....Pages 37-55 Front Matter ....Pages 57-57 Geodesic Flow Kernel and Landmarks: Kernel Methods for Unsupervised Domain Adaptation (Boqing Gong, Kristen Grauman, Fei Sha)....Pages 59-79 Unsupervised Domain Adaptation Based on Subspace Alignment (Basura Fernando, Rahaf Aljundi, Rémi Emonet, Amaury Habrard, Marc Sebban, Tinne Tuytelaars)....Pages 81-94 Learning Domain Invariant Embeddings by Matching Distributions (Mahsa Baktashmotlagh, Mehrtash Harandi, Mathieu Salzmann)....Pages 95-114 Adaptive Transductive Transfer Machines: A Pipeline for Unsupervised Domain Adaptation (Nazli Farajidavar, Teofilo de Campos, Josef Kittler)....Pages 115-132 What to Do When the Access to the Source Data Is Constrained? (Gabriela Csurka, Boris Chidlovskii, Stéphane Clinchant)....Pages 133-149 Front Matter ....Pages 151-151 Correlation Alignment for Unsupervised Domain Adaptation (Baochen Sun, Jiashi Feng, Kate Saenko)....Pages 153-171 Simultaneous Deep Transfer Across Domains and Tasks (Judy Hoffman, Eric Tzeng, Trevor Darrell, Kate Saenko)....Pages 173-187 Domain-Adversarial Training of Neural Networks (Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette et al.)....Pages 189-209 Front Matter ....Pages 211-211 Unsupervised Fisher Vector Adaptation for Re-identification (Usman Tariq, Jose A. Rodriguez-Serrano, Florent Perronnin)....Pages 213-225 Semantic Segmentation of Urban Scenes via Domain Adaptation of SYNTHIA (German Ros, Laura Sellart, Gabriel Villalonga, Elias Maidanik, Francisco Molero, Marc Garcia et al.)....Pages 227-241 From Virtual to Real World Visual Perception Using Domain Adaptation—The DPM as Example (Antonio M. López, Jiaolong Xu, José L. Gómez, David Vázquez, Germán Ros)....Pages 243-258 Generalizing Semantic Part Detectors Across Domains (David Novotny, Diane Larlus, Andrea Vedaldi)....Pages 259-273 Front Matter ....Pages 275-275 A Multisource Domain Generalization Approach to Visual Attribute Detection (Chuang Gan, Tianbao Yang, Boqing Gong)....Pages 277-289 Unifying Multi-domain Multitask Learning: Tensor and Neural Network Perspectives (Yongxin Yang, Timothy M. Hospedales)....Pages 291-309 Back Matter ....Pages 311-344