Transfer Joint Matching for Unsupervised Domain Adaptation

By Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu. 2014

717 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Immunology

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 Immunology

Citations in the corpus

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).”
Deep Hashing Network for Unsupervised Domain Adaptation (2017, methodology): “Kernel-PCA based methods apply the MMD to achieve nonlinear alignment of domains [32, 33, 38].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “domains closer, the distances between the sample means for each dimensions of the source and the target is incorporated into the objective function to be minimized. The Transfer Joint Matching9 (TJM) [40] learns a non-linear transformation between the two domains by minimizing the distance between t”
Return of Frustratingly Easy Domain Adaptation (2015, background): “Recent state-of-the-art un-supervised approaches (Gopalan, Li, and Chellappa 2011; Gong et al. 2012; Long et al. 2014; Caseiro et al. 2015) have pursued adaptation by projecting the source and target distributions into a lower-dimensional manifold, and ﬁnding a transformation that brings the…”
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation (2016, background): “A range of approaches along this line of research in object recognition have been proposed [4,5,27,28,29,30,9], most were designed specifically for small datasets such as the Office dataset [11].”
Joint Geometrical and Statistical Alignment for Visual Domain Adaptation (2017, methodology): “Transfer joint matching (TJM) [8] improves TCA by jointly reweighting the instances and finding the common subspace.”
On Learning Invariant Representations for Domain Adaptation (2019, methodology): “, the maximum mean discrepancy (MMD) (Long et al., 2014; 2015; 2016), the Wasserstein distance (Courty et al.”
Deep Model Based Domain Adaptation for Fault Diagnosis (2017, background): “The learning strategies of most published domain adaptation works can be roughly classified into two categories: instance transfer and subspace learning—the former reweights the source data according to the shared information contained in the target data, and then make a further analysis on the rewe”
Deep Transfer Learning for Few-Shot SAR Image Classification (2019, background): “The challenge of class-matching is a known problem in domain adaptation, and several approaches have been developed to address this challenge [28].”
Attention Transfer from Web Images for Video Recognition (2017, background): “ been proposed to address this problem, where the key focus is to learn domaininvariant feature representations. There are two common strategies: oneapproachistoreweighttheinstancesfromthesourcedomain[4, 22], and the other approach is to find a mapping function that would align the source distributi”
Semi-supervised Domain Adaptation with Subspace Learning for visual recognition (2015, background): “The research on domain adaptation has proceeded along three different dimensions: unsupervised domain adaptation [1, 16, 25, 26], supervised domain adaptation [2, 8, 21, 24, 28], and semi-supervised domain adaptation [9, 13, 14].”
Who's that Actor? Automatic Labelling of Actors in TV Series Starting from IMDB Images (2016, result): “We performed some experiments with Transfer Joint Matching [26], which is a global optimization procedure, but it took 60x longer to run, and gave inferior results to our baselines.”
SAR Image Classification Using Few-Shot Cross-Domain Transfer Learning (2019, background): “The challenge of classmatching is a known problem in domain adaptation and several approaches have been developed to address this challenge [20].”
Small Sample Learning in Big Data Era (2018, methodology): “And the non-linear transformation between the two domains was investigated by (Long et al., 2014) through minimizing the distance between the empirical expectations of source and target data distributions integrated within a kernel embedding.”
Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation (2015, background): “Transfer learning can be mainly categorized two subsets: homogeneous transfer learning (domain adaptation) [7, 18, 21, 14] in a single domain but with different distributions in training and testing sets, and heterogenous transfer learning [37, 8, 24] across different modalities.”
Deep Transfer Network: Unsupervised Domain Adaptation (2015, methodology): “…Learning (FSSL) [13] + NN • Transfer Component Analysis (TCA) [24] + NN • Geodesic Flow Kernel (GFK) [12] + NN • Transfer Joint Matching (TJM) [22] + NN • Regularized Least Squares (RLS) • Adaptation Regularization based Regularized Least Squares (ARRLS) [20] • Multiple Layer Perceptrons…”
Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application (2018, methodology): “As this situation is normally seen in practical problems for various fields, the domain adaptation has also received wide attention.”
Correlation Alignment for Unsupervised Domain Adaptation (2016, result): “ibution. However, this assumption rarely holds in practice, as the data are likely to change over time and space. To compensate for the degradation in performance due to domain shift, domainadaptation[23, 8, 11, 20, 28, 25, 30, 2] tries to transferknowledge from source (training) domain to target (t”