Moment Matching for Multi-Source Domain Adaptation

Peng, Xingchao; Bai, Qinxun; Xia, Xide; Huang, Zijun; Saenko, Kate; Wang, Bo

doi:10.1109/iccv.2019.00149

Cited by 1,149 publications

(1,022 citation statements)

References 29 publications

Supporting

Mentioning

1,008

Contrasting

Unclassified

Order By: Relevance

“…For supervised DA between multiple H&E stained images, Tellez et al, [82] showed that mitosis-detection and cancer tissue classification in a particular color space leads to higher accuracy. Typically, to assess domain relationship and DA direction, it is necessary to use (a) large-scale empirical studies such as [6,58] exploring bi-directional DA across multiple datasets, (b) a representation-shift metric [24] to roughly quantify the risk of applying learned-representations from a particular domain to a new domain, or (c) multi-source DA [83], which automatically explores latent source domains in multi-source datasets and quantifies the membership of each target sample. However, such experimentation requires extensive benchmarking studies that are lacking in medical imaging.…”

Section: Domain Selection and Direction Of Domain Adaptationmentioning

confidence: 99%

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Choudhary

Zhu

et al. 2020

Yearb Med Inform

View full text Add to dashboard Cite

Introduction: There has been a rapid development of deep learning (DL) models for medical imaging. However, DL requires a large labeled dataset for training the models. Getting large-scale labeled data remains a challenge, and multi-center datasets suffer from heterogeneity due to patient diversity and varying imaging protocols. Domain adaptation (DA) has been developed to transfer the knowledge from a labeled data domain to a related but unlabeled domain in either image space or feature space. DA is a type of transfer learning (TL) that can improve the performance of models when applied to multiple different datasets. Objective: In this survey, we review the state-of-the-art DL-based DA methods for medical imaging. We aim to summarize recent advances, highlighting the motivation, challenges, and opportunities, and to discuss promising directions for future work in DA for medical imaging. Methods: We surveyed peer-reviewed publications from leading biomedical journals and conferences between 2017-2020, that reported the use of DA in medical imaging applications, grouping them by methodology, image modality, and learning scenarios. Results: We mainly focused on pathology and radiology as application areas. Among various DA approaches, we discussed domain transformation (DT) and latent feature-space transformation (LFST). We highlighted the role of unsupervised DA in image segmentation and described opportunities for future development. Conclusion: DA has emerged as a promising solution to deal with the lack of annotated training data. Using adversarial techniques, unsupervised DA has achieved good performance, especially for segmentation tasks. Opportunities include domain transferability, multi-modal DA, and applications that benefit from synthetic data.

show abstract

Section: Domain Selection and Direction Of Domain Adaptationmentioning

confidence: 99%

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Choudhary

Zhu

et al. 2020

Yearb Med Inform

View full text Add to dashboard Cite

show abstract

“…Besides the marginal distributions, the output class distributions are also considered in domain adaptation [17]. In addition, multi-domain adaptation can be achieved through moment matching [18][19].…”

Section: Related Workmentioning

confidence: 99%

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Jia

Sun

2020

IEEE Access

View full text Add to dashboard Cite

Although most transfer learning methods can reduce the difference of the feature distributions between the source and target domains effectively, some classes in the two domains may still be misaligned after domain adaptation, especially for the classes with similar features such as "bicycle" and "motorcycle". Therefore, a graph regularization based adversarial network model is proposed, whose innovations mainly include the following two aspects: First, a constraint function which is used to measure the difference between the features belonged to different classes is proposed, whose purpose is that not only the training accuracy is taken into account during supervised training, but also the difference between classes should be enlarged as much as possible; Then, a graph regularization constraint function is proposed, which makes all the classes have good local preserving properties after domain adaptation, and further reduces the possibility of all classes being misaligned. Experimental results on several cross-domain benchmark datasets show that our newly proposed approach outperforms state of the art methods.

show abstract

“…MDI3D: Two popular datasets, i.e., MI3DOR [24] and DomainNet [37], are used to collect samples for MDI3D [45]. We manually choose the common 16 classes from two datasets.…”

Section: Experiments 41 Datasetmentioning

confidence: 99%

“…We manually choose the common 16 classes from two datasets. 2D images are from three domains, including real images (from MI3DOR), sketch images (from DomainNet [37]) and quick draw images (from Do-mainNet [37]). The 3D objects are from MI3DOR [24].…”

Section: Experiments 41 Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Domain-Specific Alignment Network for Multi-Domain Image-Based 3D Object Retrieval

Song

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

2D image-based 3D object retrieval is a very important task in computer vision and big data management. Conventional image-based 3D object retrieval usually assumes that the images are from one single domain. However, for real applications, 2D images may be from multiple domains (e.g., real image, sketch, and quick draw). It raises significant challenges for this task since these 2D images have a great domain gap with each other as well as a great modality gap with 3D objects. To address these issues, we propose an unsupervised Domain-Specific Alignment Network (DSAN) for multidomain image-based 3D object retrieval. The proposed method aims to reduce domain discrepancy by domain-specific alignment network with multi-level moment matching, including first-order moment and second-order moment. Based on the observation that for any given sample, different domain classifiers should output the same label, we design a domain-specific classifier alignment module. To our knowledge, the proposed method is the first unsupervised work to align multiple-domain 2D images with 3D objects in an end-to-end manner. The multi-domain dataset MDI3D is utilized to advocate the research on this task, and the extensive experimental results demonstrate the superiority of the proposed method. CCS CONCEPTS • Computing methodologies → Computer vision; Visual contentbased indexing and retrieval; • Information systems → Multimedia and multimodal retrieval.

show abstract

Moment Matching for Multi-Source Domain Adaptation

Cited by 1,149 publications

References 29 publications

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Domain-Specific Alignment Network for Multi-Domain Image-Based 3D Object Retrieval

Contact Info

Product

Resources

About