Domain Adaptation via Transfer Component Analysis

By Sinno Jialin Pan, Ivor Wai-Hung Tsang, James T. Kwok, Qiang Yang. 2009

4,470 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Signal Processing

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 Representation & Self-Supervised Learning

In Signal Processing

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, methodology): “There are also methods seeking a domain transition from the source domain to the target domain (Gong et al., 2012; Gopalan et al., 2011; Pan et al., 2011).”
Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines (2018, background): “The input distribution (domain) difference has been discussed extensively in the setting of transfer learning [15], primarily as a domain adaptation problem [16].”
Domain-Adversarial Training of Neural Networks (2015, background): “…or selecting samples from the source domain (Borg-wardt et al., 2006; Huang et al., 2006; Gong et al., 2013), while others seek an explicit feature space transformation that would map source distribution into the target one (Pan et al., 2011; Gopalan et al., 2011; Baktashmotlagh et al., 2013).”
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).”
Kernel Mean Embedding of Distributions: A Review and Beyonds (2016, background): “…and Gretton 2014), causal discovery (Sgouritsa et al. 2013, Chen et al. 2014, Schölkopf et al. 2015), covariate shift (Gretton et al. 2009, Pan et al. 2011) and domain adaptation (Blanchard et al. 2011, Muandet et al. 2013), selection bias correction (Huang et al. 2007), herding (Chen et…”
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 Generalization via Invariant Feature Representation (2013, methodology): “If there are two domains, source P S and target P T , then UDICA is closely related – though not identical to – Transfer Component Analysis (Pan et al. 2011).”
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].”
Deep Domain Confusion: Maximizing for Domain Invariance (2014, background): “In fact, the size of a domain shift is often measured by the distance between the source and target subspace representations [6, 13, 23, 26, 28].”
Meta-Transfer Learning for Few-Shot Learning (2018, background): “Transfer learning What and how to transfer are key issues to be addressed in transfer learning, as different methods are applied to different source-target domains and bridge different transfer knowledge [34, 56, 54, 58].”
A Comprehensive Survey on Transfer Learning (2019, methodology): “TCA adopts MMD to measure the marginal distribution difference and enforces the scatter matrix as the constraint.”
A Survey on Deep Transfer Learning (2018, methodology): “New Data Space Transfer component analysis (TCA) introduced by [18] and TCA-based meth-ods [29] had been widely used in many applications of traditional transfer learning.”
Deep Hashing Network for Unsupervised Domain Adaptation (2017, methodology): “The features are fixed and then a model is trained to align the source and target domains [16, 20, 33, 38, 42, 43, 44].”
Deep CORAL: Correlation Alignment for Deep Domain Adaptation (2016, methodology): “We compare to 7 recently published methods: CNN [20] (no adaptation), GFK [7], SA [8], TCA [22], CORAL [1], DDC [16], DAN [17].”