Supervised Representation Learning: Transfer Learning with Deep Autoencoders

By Fuzhen Zhuang, Xiaohu Cheng, Ping Luo, Sinno Jialin Pan, Qing He. 2015

370 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Towards Explainable Deep Neural Networks (xDNN) (2019, background): “Transfer learning helps to considerably reduce the amount of time used for training, moreover, it also may helps to improve the accuracy of the models [9].”
Moment Matching for Multi-Source Domain Adaptation (2018, methodology): “Other commonly used methods include correlation alignment [39, 32], Kullback-Leibler (KL) divergence [51], and H divergence [1].”
A Comprehensive Survey on Transfer Learning (2019, background): “[44], [134] proposes an approach termed transfer learning with deep autoencoders (TLDAs).”
Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning (2017, methodology): “In contrast, the authors in Zhuang et al. (2015) do so by minimizing a modified version of the Kullback-Leibler divergence of the mean activations (MKL).”
On the Impact of Data Set Size in Transfer Learning Using Deep Neural Networks (2016, background): “Similarly, [79] attempts to increase transferability of features by training deep autoencoders, with two encoding layers.”
Transfer Learning with Dynamic Adversarial Adaptation Network (2019, methodology): “For instance, Correlation Alignment (CORAL) [17], Kullback-Leibler (KL) divergence [31], Maximum Mean Discrepancy (MMD) [32], [21], [33], [34], [15], and Central Moment Discrepancy (CMD) [35] are used to reduce the distribution divergence between domains.”
Maximum Density Divergence for Domain Adaptation (2020, unknown): “In existing works, four distance metrics have been explored: 1) MMD [16], [17], [24], 2) Covariance [15], 3) Hdivergence [18] and 4)Kullback–Leibler (KL) divergence [25].”
Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation (2018, background): “Therefore, some recent works start to apply deep neural networks to bridge the source and target domains to perform domain adaptation (Zhuang et al. 2015; Shu et al. 2015; Hubert Tsai, Yeh, and Frank Wang 2016; Zhou et al. 2014).”
Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation (2020, background): “ec model to evaluate the natural distances between dierent domains. Deep Feature Disentanglement Deep neural networks are known to extract features where multiple hidden factors are highly entangled [41]. Learning disentangled representations can help to model the relevant factors of data variation ”
Wasserstein Distance Guided Representation Learning for Domain Adaptation (2017, methodology): “Other domain adaptation frameworks (Bousmalis et al. 2016; Tzeng et al. 2014; Long et al. 2015; 2016; Zhuang et al. 2015) are not included in the comparison, because these frameworks focus on adaptation architecture design and all compared approaches can be easily integrated into these frameworks.”
Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation (2020, methodology): “For unsupervised domain adaptation, a major line of work reduces the domain gap by learning domain invariant feature representation, such as Maximum Mean Discrep-ancy (MMD) [38, 30], Correlation Alignment (CORAL) [ 36, 24] and Kullback-Leiber divergence (KL) [51].”
Deep Visual Domain Adaptation: A Survey (2018, methodology): “Reconstructionbased using the data reconstruction as an auxiliary task to ensure feature invariance encoder-decoder reconstruction [4, 26, 24, 114] adversarial reconstruction [105, 113, 50]”