Unsupervised Domain Adaptation by Domain Invariant Projection

By Mahsa Baktash, Mehrtash Harandi, Brian C. Lovell, Mathieu Salzmann. 2013

462 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Unsupervised Domain Adaptation by Backpropagation (2014, neutral): “Some approaches perform this by reweighing or selecting samples from the source domain [3, 11, 7], while others seek an explicit feature space transformation that would map source distribution into the target ones [16, 10, 2].”
Semi-Supervised QA with Generative Domain-Adaptive Nets (2017, background): “Another line of research on domain adaptation attempt to match the distance between different domain distributions in a low dimensional space (Long et al., 2015; Baktashmotlagh et al., 2013).”
Domain-Adversarial Training of Neural Networks (2015, background): “Over the years, a large part of the literature has focused mainly on linear hypothesis (see for instance Blitzer et al., 2006; Bruzzone and Marconcini, 2010; Germain et al., 2013; Baktashmotlagh et al., 2013; Cortes and Mohri, 2014).”
Learning Transferable Features with Deep Adaptation Networks (2015, methodology): “A rich line of prior works have focused on learning shallow features by jointly minimizing a distance metric of domain discrepancy (Pan et al., 2011; Long et al., 2013; Baktashmotlagh et al., 2013; Gong et al., 2013; Zhang et al., 2013; Ghifary et al., 2014; Wang & Schneider, 2014).”
Domain Generalization via Conditional Invariant Representations (2018, background): “2007) or domain-invariant feature learning (Pan et al. 2011; Baktashmotlagh et al. 2013), using unlabeled data from source and target domains.”
Domain Adaptation with Conditional Transferable Components (2016, methodology): “Other methods learn a low dimensional projection by explicitly minimizing the discrepancy between the distributions of projected features on source and target domains (Pan et al., 2011; Long et al., 2014; 2015; Baktashmotlagh et al., 2013; Si et al., 2010; 2011; Muan-det et al., 2013).”
Few-Shot Adversarial Domain Adaptation (2017, background): “Others find a shared latent space that both domains can be mapped to before classification [35, 2, 39, 13, 14, 41, 37, 38].”
Unified Deep Supervised Domain Adaptation and Generalization (2017, background): “The second one seeks to find a shared latent space for source and target distributions [40, 2, 44, 21, 22, 47, 43].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “[10] propose the Domain Invariant Projection 6 (DIP) approach that compares directly the distributions in the RKHS while constraining the transformation to be orthogonal.”
Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning (2017, methodology): “We consider the unsupervised domain adaptation setting (Glorot et al., 2011; Li et al., 2014; Pan et al., 2011; Ganin et al., 2016) with an input space X and a label space Y .”
Domain Adaptive Neural Networks for Object Recognition (2014, methodology): “For the MMD regularization, we set the standard deviation s of the Gaussian kernel by the following calculation: s = MSD 2 (Baktashmotlagh et al., 2013), where MSD is the median squared distance between all source samples.”
Revisiting Batch Normalization For Practical Domain Adaptation (2016, methodology): “ing Kernel Hilbert Space, and then compute the dierence of sample means. To reduce dataset discrepancies, many methods are proposed, including sample selections [13,14], explicit projection learning [15,16,17] and principal axes alignment [18,19]. All of these methods face the same challenge of devi”
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification (2019, background): “, 2013), finding domain-invariant spaces (Baktashmotlagh et al., 2013; Ganin et al., 2016), feature augmentation (Blitzer et al.”
A Review of Domain Adaptation without Target Labels (2019, methodology): “The manifold assumption is interesting, because it implies that there exists a path along the manifold’s surface from the source to the target domain [127], [128].”
Visual Domain Adaptation with Manifold Embedded Distribution Alignment (2018, methodology): “DIP mainly focused on feature transformation and only aligned marginal distributions.”
Causal Generative Domain Adaptation Networks (2018, methodology): “We use a mixture of RBF kernels k ( x, x (cid:48) ) = =1 k σ q ( x, x (cid:48) ) in MMD.”