A Survey of Unsupervised Deep Domain Adaptation

Wilson, Garrett; Cook, Diane J.

doi:10.1145/3400066

Cited by 645 publications

(347 citation statements)

References 147 publications

Supporting

Mentioning

307

Contrasting

Order By: Relevance

“…DL-based DA is achieved using various representation learning strategies such as aligning the domain distributions, learning a mapping between domains, separating normalization statistics, and ensemble-based approaches [32][33][34]. As shown in Figure 2-a, there are two families of DA approaches for medical imaging: (a) Domain Transformation (DT-DA) translates images from one domain to the other domain, so that the obtained models can be directly applied to all images, and (b) Latent Feature Space Transformation (LFST-DA) aligns images from both domains in a common hidden feature space to train the task model on top of the hidden features.…”

Section: Deep Learning-based 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: Deep Learning-based 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

“…Within these approaches, the most classical assumption is that the labeled and the unlabeled data are drawn from the same distribution and one aims at using the unlabeled data (via annotations or pretext tasks) to solve the same tasks for which the labeled data was annotated. However, in practice, we may require to solve new tasks, leading to transfer learning (TL) [46,54], or solving the same tasks in a new domain, leading to domain adaptation (DA) [10,43,47]. Beyond specific techniques to tackle TL or DA, we can leverage solutions/ideas from AL, SSL, or SfSL.…”

Section: B the Domain Adaptation Problemmentioning

confidence: 99%

“…In unsupervised DA (UDA), X T is unlabeled; thus, we address the more challenging situations of using X T with either φ S or X l,tr S to train φ T . For a review of the DA corpus we advise the reader to consult [10,43,47].…”

Section: B Domain Adaptationmentioning

confidence: 99%

Co-Training for On-Board Deep Object Detection

Villalonga

Peña

2020

IEEE Access

View full text Add to dashboard Cite

Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features and shallow machine learning and, despite its unprecedented performance gains, the problem remains open within the deep learning paradigm due to its data-hungry nature. Best performing deep vision-based object detectors are trained in a supervised manner by relying on human-labeled bounding boxes which localize class instances (i.e. objects) within the training images. Thus, object detection is one of such tasks for which human labeling is a major bottleneck. In this paper, we assess co-training as a semi-supervised learning method for self-labeling objects in unlabeled images, so reducing the human-labeling effort for developing deep object detectors. Our study pays special attention to a scenario involving domain shift; in particular, when we have automatically generated virtualworld images with object bounding boxes and we have real-world images which are unlabeled. Moreover, we are particularly interested in using co-training for deep object detection in the context of driver assistance systems and/or self-driving vehicles. Thus, using well-established datasets and protocols for object detection in these application contexts, we will show how co-training is a paradigm worth to pursue for alleviating object labeling, working both alone and together with task-agnostic domain adaptation.

show abstract

“…There are many studies on GANs [13][14][15]24,[32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47]. In this section, we investigate the studies that consider the stability problem during the training of GANs.…”

Section: Related Workmentioning

confidence: 99%

“…Covariate shift analysis was a scheme to add a multi-class classifier in a balanced multi-class dataset to investigate whether the data generated by GAN was biased [44]. Unsupervised deep domain adaptation was a scheme to extend covariate shift analysis to an unbalanced dataset with the existence of a balanced dataset [45].…”

Section: Analyzing the Stability Of The Gan Modelmentioning

confidence: 99%

Simplified Fréchet Distance for Generative Adversarial Nets

Kim

Jung

et al. 2020

Sensors

View full text Add to dashboard Cite

We introduce a distance metric between two distributions and propose a Generative Adversarial Network (GAN) model: the Simplified Fréchet distance (SFD) and the Simplified Fréchet GAN (SFGAN). Although the data generated through GANs are similar to real data, GAN often undergoes unstable training due to its adversarial structure. A possible solution to this problem is considering Fréchet distance (FD). However, FD is unfeasible to realize due to its covariance term. SFD overcomes the complexity so that it enables us to realize in networks. The structure of SFGAN is based on the Boundary Equilibrium GAN (BEGAN) while using SFD in loss functions. Experiments are conducted with several datasets, including CelebA and CIFAR-10. The losses and generated samples of SFGAN and BEGAN are compared with several distance metrics. The evidence of mode collapse and/or mode drop does not occur until 3000k steps for SFGAN, while it occurs between 457k and 968k steps for BEGAN. Experimental results show that SFD makes GANs more stable than other distance metrics used in GANs, and SFD compensates for the weakness of models based on BEGAN-based network structure. Based on the experimental results, we can conclude that SFD is more suitable for GAN than other metrics.

show abstract

A Survey of Unsupervised Deep Domain Adaptation

Cited by 645 publications

References 147 publications

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Co-Training for On-Board Deep Object Detection

Simplified Fréchet Distance for Generative Adversarial Nets

Contact Info

Product

Resources

About