Visual Domain Adaptation with Manifold Embedded Distribution Alignment

Wang, Jindong; Feng, Wenjie; Chen, Yiqiang; Yu, Han; Huang, Mei‐Yu; Yu, Philip S.

doi:10.1145/3240508.3240512

Cited by 480 publications

(292 citation statements)

References 36 publications

Supporting

Mentioning

289

Contrasting

Unclassified

Order By: Relevance

“…But these works treat the two distributions equally and fail to leverage the different importance of distributions. Recently, Wang et al proposed Balanaced Distribution Adaptation (BDA) [8] and Manifold Embedded Distribution Alignment (MEDA) [7] approaches to dynamically evaluate the different effect of marginal and conditional distributions and achieved the state-of-the-art results on domain adaptation. However, MEDA is based on kernel method and requires to train several linear classifiers in each iteration.…”

Section: Related Work a Unsupervised Domain Adaptationmentioning

confidence: 99%

“…Note that there is no need to explicitly build extra classifiers in order to compute the local distances such as MEDA [7]. In DAAN, they can be easily implemented by taking advantages of the global and local domain discriminators.…”

Section: Dynamic Adversarial Factor ωmentioning

confidence: 99%

“…4. It can be seen that the classification accuracy varies with different values of ω, which indicates the necessity to consider the different effects can be verified in BDA [8] and MEDA [7]), but also in adversarial transfer learning. Moreover, We find that the value of optimal ω varies on different tasks and even for the same task, ω may have several optimal values.…”

Section: E Analysis Of the Importance Of The Dynamic Adversarial Facmentioning

confidence: 99%

“…1), the local distribution should be given more attention. Two more recent work called Balanced Distribution Adaptation (BDA) [8] and Manifold Embedded Distribution Alignment (MEDA) [7] proposed to adaptively align these two distributions, while it is based on kernel method with high computational cost. In addition, MEDA is incapable of handling large-scale data.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Transfer Learning with Dynamic Adversarial Adaptation Network

Wang

Chen

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

Self Cite

208

View full text Add to dashboard Cite

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global source and target distributions, or pay attention to align subdomains based on multiple discriminators. However, in real applications, the marginal (global) and conditional (local) distributions between domains are often contributing differently to the adaptation. There is currently no method to dynamically and quantitatively evaluate the relative importance of these two distributions for adversarial learning. In this paper, we propose a novel Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluate the relative importance of global and local domain distributions. To the best of our knowledge, DAAN is the first attempt to perform dynamic adversarial distribution adaptation for deep adversarial learning. DAAN is extremely easy to implement and train in real applications. We theoretically analyze the effectiveness of DAAN, and it can also be explained in an attention strategy. Extensive experiments demonstrate that DAAN achieves better classification accuracy compared to stateof-the-art deep and adversarial methods. Results also imply the necessity and effectiveness of the dynamic distribution adaptation in adversarial transfer learning.

show abstract

Section: Related Work a Unsupervised Domain Adaptationmentioning

confidence: 99%

Section: Dynamic Adversarial Factor ωmentioning

confidence: 99%

Section: E Analysis Of the Importance Of The Dynamic Adversarial Facmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Transfer Learning with Dynamic Adversarial Adaptation Network

Wang

Chen

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

Self Cite

208

View full text Add to dashboard Cite

show abstract

“…Its main idea is to leverage the data from auxiliary subjects (called source subjects or source domains) to improve the learning performance for a new subject (called target subject or target domain). A popular idea in DA is to project the source domain and target domain data into low dimensional subspaces where the geometrical shift or/and distribution shift are reduced, such as joint distribution adaptation (JDA) [22], joint geometrical and statistical alignment (JGSA) [23], and manifold embedded distribution alignment (MEDA) [24]. Computational intelligence techniques have also been used in transfer learning, as reviewed by Lu et al [25].…”

Section: Introductionmentioning

confidence: 99%

Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach

2020

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

A brain-computer interface (BCI) system usually needs a long calibration session for each new subject/task to adjust its parameters, which impedes its transition from the laboratory to real-world applications. Domain adaptation, which leverages labeled data from auxiliary subjects/tasks (source domains), has demonstrated its effectiveness in reducing such calibration effort. Currently, most domain adaptation approaches require the source domains to have the same feature space and label space as the target domain, which limits their applications, as the auxiliary data may have different feature spaces and/or different label spaces. This paper considers different set domain adaptation for BCIs, i.e., the source and target domains have different label spaces. We introduce a practical setting of different label sets for BCIs, and propose a novel label alignment (LA) approach to align the source label space with the target label space. It has three desirable properties: 1) LA only needs as few as one labeled sample from each class of the target subject; 2) LA can be used as a preprocessing step before different feature extraction and classification algorithms; and, 3) LA can be integrated with other domain adaptation approaches to achieve even better performance. Experiments on two motor imagery datasets demonstrated the effectiveness of LA.

show abstract

Source‐enhanced prototypical alignment for single image 3D model retrieval

Song

Wang

Zhang

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Single image 3D model retrieval has attracted a lot of attentions with the convenience of organizing large-scale unlabeled 3D models. Existing methods transfer the knowledge from well-annotated 2D images (i.e., source domain) to unlabeled 3D models (i.e., target domain) to improve the discriminability of 3D models and align the feature distributions of 2D images and 3D models. However, during the alignment, the feature learning target of improving the discriminability of 3D models sometimes confuses the boundaries between 2D image categories, where prior methods ignore keeping the discriminability of 2D images. Motivated by this observation, we propose a source-enhanced prototypical alignment framework to first remain the discriminability of 2D images and then guide the category-level cross-domain alignment with better image representations. Specifically, a novel separation and compactness loss is proposed for images to separate the samples from different categories and compact the samples within the same category. Then we perform prototypical alignment to make 2D image features assist in the discriminative feature learning for 3D models. We evaluate the proposed method on the commonly used cross-domain 3D model retrieval benchmarks, namely MI3DOR and MI3DOR-2, and the results demonstrate the effectiveness of the proposed method.

show abstract

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

Cited by 480 publications

References 36 publications

Transfer Learning with Dynamic Adversarial Adaptation Network

Transfer Learning with Dynamic Adversarial Adaptation Network

Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach

Source‐enhanced prototypical alignment for single image 3D model retrieval

Contact Info

Product

Resources

About