Transfer Independently Together: A Generalized Framework for Domain Adaptation

Li, Jingjing; Lü, Ke; Huang, Zi; Zhu, Lei; Shen, Heng Tao

doi:10.1109/tcyb.2018.2820174

Cited by 250 publications

(71 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, there are also some works to learn an intermediate space shared by the visual features and semantic features [4,38,39]. Besides, ZSL is also related with domain adaptation and cold-start recommendation [18][19][20][21].…”

Section: Zero-shot Learningmentioning

confidence: 99%

Leveraging the Invariant Side of Generative Zero-Shot Learning

Jing

Lü

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

314

207

View full text Add to dashboard Cite

Conventional zero-shot learning (ZSL) methods generally learn an embedding, e.g., visual-semantic mapping, to handle the unseen visual samples via an indirect manner. In this paper, we take the advantage of generative adversarial networks (GANs) and propose a novel method, named leveraging invariant side GAN (LisGAN), which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions. Specifically, we train a conditional Wasserstein GANs in which the generator synthesizes fake unseen features from noises and the discriminator distinguishes the fake from real via a minimax game. Considering that one semantic description can correspond to various synthesized visual samples, and the semantic description, figuratively, is the soul of the generated features, we introduce soul samples as the invariant side of generative zero-shot learning in this paper. A soul sample is the meta-representation of one class. It visualizes the most semantically-meaningful aspects of each sample in the same category. We regularize that each generated sample (the varying side of generative ZSL) should be close to at least one soul sample (the invariant side) which has the same class label with it. At the zero-shot recognition stage, we propose to use two classifiers, which are deployed in a cascade way, to achieve a coarse-to-fine result. Experiments on five popular benchmarks verify that our proposed approach can outperform state-of-the-art methods with significant improvements 1 .

show abstract

Section: Zero-shot Learningmentioning

confidence: 99%

Leveraging the Invariant Side of Generative Zero-Shot Learning

Jing

Lü

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

314

207

View full text Add to dashboard Cite

show abstract

“…According to the property of sample features, domain adaptation can be categorized as homogeneous domain adaptation [6], [18], [29] and heterogeneous domain adaptation [19], [20], [30]. In homogeneous domain adaptation, the data from both domains are sampled from the same feature space.…”

Section: A Domain Adaptationmentioning

confidence: 99%

“…According to the constrained optimization theory, we introduce a Lagrange multiplier Φ, and get the Lagrange function for Eq. (19) as follows:…”

Section: ) Overallmentioning

confidence: 99%

Locality Preserving Joint Transfer for Domain Adaptation

Jing

Lü

et al. 2019

IEEE Trans. on Image Process.

Self Cite

241

View full text Add to dashboard Cite

Domain adaptation aims to leverage knowledge from a well-labeled source domain to a poorly-labeled target domain. A majority of existing works transfer the knowledge at either feature level or sample level. Recent researches reveal that both of the paradigms are essentially important, and optimizing one of them can reinforce the other. Inspired by this, we propose a novel approach to jointly exploit feature adaptation with distribution matching and sample adaptation with landmark selection. During the knowledge transfer, we also take the local consistency between samples into consideration, so that the manifold structures of samples can be preserved. At last, we deploy label propagation to predict the categories of new instances. Notably, our approach is suitable for both homogeneous and heterogeneous domain adaptation by learning domain-specific projections. Extensive experiments on five open benchmarks, which consist of both standard and large-scale datasets, verify that our approach can significantly outperform not only conventional approaches but also end-to-end deep models. The experiments also demonstrate that we can leverage handcrafted features to promote the accuracy on deep features by heterogeneous adaptation. Our codes are available at https://github.com/lijin118/LPJT.

show abstract

“…Moreover, some deep neural networks (DNN) based models [16]- [18] are proposed to extract nonlinear features with stronger representation power. It is worth mentioning that some work in other related areas also provided feasible solutions, such as low-rank coding [19], Gaussian Process Latent Variable Model (GPLVM) [20] or Maximum Mean Discrepancy (MMD) [21], [22]. Despite promising results on real applications, aforementioned MvSL based methods will fail to work, when the view information of test samples is unknown in advance [23].…”

Section: Introductionmentioning

confidence: 99%

Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning

Wang

Peng

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Low-rank Multi-view Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL based methods are incapable of well handling view discrepancy and discriminancy simultaneously, which thus leads to the performance degradation when there is a large discrepancy among multi-view data. To circumvent this drawback, motivated by the block-diagonal representation learning, we propose Structured Low-rank Matrix Recovery (SLMR), a unique method of effectively removing view discrepancy and improving discriminancy through the recovery of structured low-rank matrix. Furthermore, recent low-rank modeling provides a satisfactory solution to address data contaminated by predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution. However, these models are not practical since complicated noise in practice may violate those assumptions and the distribution is generally unknown in advance. To alleviate such limitation, modal regression is elegantly incorporated into the framework of SLMR (term it MR-SLMR). Different from previous LMvSL based methods, our MR-SLMR can handle any zero-mode noise variable that contains a wide range of noise, such as Gaussian noise, random noise and outliers. The alternating direction method of multipliers (ADMM) framework and half-quadratic theory are used to efficiently optimize MR-SLMR. Experimental results on four public databases demonstrate the superiority of MR-SLMR and its robustness to complicated noise.

show abstract

Transfer Independently Together: A Generalized Framework for Domain Adaptation

Cited by 250 publications

References 35 publications

Leveraging the Invariant Side of Generative Zero-Shot Learning

Leveraging the Invariant Side of Generative Zero-Shot Learning

Locality Preserving Joint Transfer for Domain Adaptation

Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning

Contact Info

Product

Resources

About