Generalized Transfer Subspace Learning Through Low-Rank Constraint

By Ming Shao, Dmitry Kit, Yun Raymond Fu. 2014

306 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics

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 Computational Mechanics

Citations in the corpus

Domain Generalization via Conditional Invariant Representations (2018, background): “Domain adaptation is a related problem which has been extensively studied in the literature (Baktashmotlagh et al. 2013; Huang et al. 2007; Pan et al. 2011; Long et al. 2017; Shao, Kit, and Fu 2014; Shao et al. 2016; Luo et al. 2017; Liu, Yang, and Tao 2017; ?”
An introduction to domain adaptation and transfer learning (2018, background): “The reconstruction error from the subspace to original space should be minimal [171].”
Spectral Bisection Tree Guided Deep Adaptive Exemplar Autoencoder for Unsupervised Domain Adaptation (2016, methodology): “Recently, low-rank coding has been applied to transfer learning scenario to guide the shared subspace learning (Shao, Kit, and Fu 2014; Ding, Shao, and Fu 2015), as it can derive a locality-awareness reconstruction between domains, where source and target data are accurately aligned: min Z rank(Z),…”
Robust Unsupervised Cross-modal Hashing for Multimedia Retrieval (2020, background): “To achieve the first mission, inspired by transfer learning [31], we assume that each object from one modality can be linearly represented by the objects from the other modality in the common space.”
Structure-Preserved Multi-source Domain Adaptation (2016, methodology): “Typical methods include finding intermediate subspaces that describe the smooth transition from one domain to another [8], [10], [14], [23], learning common features subspace [3], [24], [27], [29], [31] or deep features [6], [28].”
A Unified Framework for Metric Transfer Learning (2017, background): “[25] attempted to impose a low-rank constraint to match the source domain and the target domain in the subspace for transfer learning.”
A Review of Domain Adaptation without Target Labels (2019, methodology): “The reconstruction error then consists of the mismatch between the reconstructed source samples and the target samples, measured through the squared error or the Frobenius norm for instance [147].”
Maximum Density Divergence for Domain Adaptation (2020, background): “A slight change in the training domain can lead to destructive result variation in the test domain [3], [5], [6].”