Domain Conditioned Adaptation Network

Li, Shuang; Liu, Chi Harold; Lin, Qiuxia; Xie, Binhui; Ding, Zhengming; Huang, Gao; Tang, Jian

doi:10.1609/aaai.v34i07.6801

Cited by 83 publications

(29 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparison with previous methods Table 1 reports the performances of the proposed method compared with state-of-the-art depth predicting methods [19,22,23,24] and the most commonly-used domain adaptation algorithms [25,26,27]. For the source domain, it can be seen that our method is able to generate a depth map similar to the ground truth as shown in top row of Fig.…”

Section: Resultsmentioning

confidence: 96%

Cross-Domain Depth Estimation Network for 3D Vessel Reconstruction in OCT Angiography

Liu

Zhang

et al. 2021

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

View full text Add to dashboard Cite

Optical Coherence Tomography Angiography (OCTA) has been widely used by ophthalmologists for decision-making due to its superiority in providing caplillary details. Many of the OCTA imaging devices used in clinic provide high-quality 2D en face representations, while their 3D data quality are largely limited by low signal-to-noise ratio and strong projection artifacts, which restrict the performance of depthresolved 3D analysis. In this paper, we propose a novel 2D-to-3D vessel reconstruction framework based on the 2D en face OCTA images. This framework takes advantage of the detailed 2D OCTA depth map for prediction and thus does not rely on any 3D volumetric data. Based on the data with available vessel depth labels, we first introduce a network with structure constraint blocks to predict the depth of blood vessels in other cross-domain en face OCTA data with unavailable labels. Afterwards, a depth adversarial adaptation module is proposed for better unsupervised cross-domain training, since images captured using different devices may suffer from varying image contrast and noise levels. Finally, vessels are reconstructed in 3D space by utilizing the estimated depth map and 2D vascular information. Experimental results demonstrate the effectiveness of our method and its potential to guide subsequent vascular analysis in 3D domain.

show abstract

Section: Resultsmentioning

confidence: 96%

Cross-Domain Depth Estimation Network for 3D Vessel Reconstruction in OCT Angiography

Liu

Zhang

et al. 2021

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

View full text Add to dashboard Cite

show abstract

“…Class-level methods align the conditional distribution based on pseudo-labels (Chen et al, 2020a;Luo et al, 2020a;Li et al, 2020b;Jiang et al, 2020;Liang et al, 2020;Venkat et al, 2020). Conditional alignment methods (Xie et al, 2018;Long et al, 2018) minimize the discrepancy between conditional distributions.…”

Section: Related Workmentioning

confidence: 99%

“…Domain alignment methods include DAN (Long et al, 2015), DANN (Ganin et al, 2016), JAN (Long et al, 2017a). Class-level methods include conditional alignment methods (CDAN (Long et al, 2018), DCAN (Li et al, 2020b), ALDA (Chen et al, 2020b)), and contrastive methods (DRMEA (Luo et al, 2020a), ETD (Li et al, 2020c), DADA (Tang and Jia, 2020b), SAFN Xu et al (2019)). We only report available results in each baseline.…”

Section: Baselinesmentioning

confidence: 99%

Domain Adaptation via Maximizing Surrogate Mutual Information

Zhao¹,

Ma²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA), which is an important topic in transfer learning, aims to predict unlabeled data from target domain with access to labeled data from the source domain. In this work, we propose a novel framework called SIDA (Surrogate Mutual Information Maximization Domain Adaptation) with strong theoretical guarantees. To be specific, SIDA implements adaptation by maximizing mutual information (MI) between features. In the framework, a surrogate joint distribution models the underlying joint distribution of the unlabeled target domain. Our theoretical analysis validates SIDA by bounding the expected risk on target domain with MI and surrogate distribution bias. Experiments show that our approach is comparable with state-of-the-art unsupervised adaptation methods on standard UDA tasks. 1

show abstract

“…DUCDA [54] develops an attention transfer mechanism for DA, which transfers the knowledge of discriminative patterns of source images to target. Differently, instead of exploring the space attention knowledge, DCAN [19] explores the low-level domaindependent knowledge in the channel attention.…”

Section: Related Workmentioning

confidence: 99%

Semantic Concentration for Domain Adaptation

Li¹,

Xie²,

Lv³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain. A mainstream of DA methods is to align the feature distributions of the two domains. However, the majority of them focus on the entire image features where irrelevant semantic information, e.g., the messy background, is inevitably embedded. Enforcing feature alignments in such case will negatively influence the correct matching of objects and consequently lead to the semantically negative transfer due to the confusion of irrelevant semantics. To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions. Specifically, we train the classifier to class-wisely maximize the prediction distribution divergence of each sample pair, which enables the model to find the region with large differences among the same class of samples. Meanwhile, the feature extractor attempts to minimize that discrepancy, which suppresses the features of dissimilar regions among the same class of samples and accentuates the features of principal parts. As a general method, SCDA can be easily integrated into various DA methods as a regularizer to further boost their performance. Extensive experiments on the cross-domain benchmarks show the efficacy of SCDA.

show abstract

Domain Conditioned Adaptation Network

Cited by 83 publications

References 52 publications

Cross-Domain Depth Estimation Network for 3D Vessel Reconstruction in OCT Angiography

Cross-Domain Depth Estimation Network for 3D Vessel Reconstruction in OCT Angiography

Domain Adaptation via Maximizing Surrogate Mutual Information

Semantic Concentration for Domain Adaptation

Contact Info

Product

Resources

About