Cross-Domain Detection via Graph-Induced Prototype Alignment

Xu, Minghao; Wang, Hang; Ni, Bingbing; Tian, Qi; Zhang, Wenjun

doi:10.1109/cvpr42600.2020.01237

Cited by 186 publications

(133 citation statements)

References 32 publications

Supporting

Mentioning

133

Contrasting

Order By: Relevance

“…The most related works to our method are [13], [17] based on the graph-inducted prototype alignment mechanism and conditional domain adversarial networks, but still differ from our method in several aspects. These works are not used for the field of unsupervised domain adaptation for crossmodal biomedical image segmentation.…”

Section: Related Workmentioning

confidence: 99%

“…More specifically, the difference between [17] and our proposed CDD module is that conditional adversarial domain adaptation is a common operation in the classifier tasks but rarely in segmentation tasks, especially in the field of unsupervised domain adaptation on cross-modal medical image segmentation. The difference between [13] and the proposed CCPA is that [13] is only suitable for object detection tasks because it performs graph-induced prototype alignment on the bounding-box level. However, the proposed CCPA module extends [13] to the pixel-level for segmentation tasks.…”

Section: Related Workmentioning

confidence: 99%

“…The difference between [13] and the proposed CCPA is that [13] is only suitable for object detection tasks because it performs graph-induced prototype alignment on the bounding-box level. However, the proposed CCPA module extends [13] to the pixel-level for segmentation tasks. We use a learnable graph attention layer to obtain the adjacency matrix of the graph at the pixel-level instead of calculating weights between region proposals at the bounding-box level.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, multilevel discriminators may come at a contradiction in the adversarial adaptation procedure given the complex combinations of cross-modality between domains. In addition, domain classifiers tend to capture global-level discrepancy features across both domains, ignoring distinct modal information of instances in the cross-modality scenario, especially when neighboring structures contain unclear boundaries or relatively homogeneous tissues [6], and combining the feature-level and instance-level alignment of the source and target domains makes it difficult to perfectly address domain shift [13]- [16].…”

Section: Introductionmentioning

confidence: 99%

“…Our method incorporates the CDD module inspired by [17] into the existing architecture to model the multimodal information and joint distributions of multilevel features via a randomized router, which makes it easier to fully capture multiplicative interactions between feature representation and segmentation prediction for domain adaptation. In CCPA, we extend category-level prototype alignment to cross-domain segmentation tasks, inspired by [13], [14], to guarantee the discriminability by exploiting more precise instance-level features. In addition, it can mitigate the negative effect of class imbalance on domain adaptation via an entropy-based loss to control the process of adaptation during the training phase.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Unsupervised Domain Adaptation Network With Category-Centric Prototype Aligner for Biomedical Image Segmentation

Gong

Sun

et al. 2021

IEEE Access

View full text Add to dashboard Cite

With the widespread success of deep learning in biomedical image segmentation, domain shift becomes a critical and challenging problem, as the gap between two domains can severely affect model performance when deployed to unseen data with heterogeneous features. To alleviate this problem, we present a novel unsupervised domain adaptation network, for generalizing models learned from the labeled source domain to the unlabeled target domain for cross-modality biomedical image segmentation. Specifically, our approach consists of two key modules, a conditional domain discriminator (CDD) and a category-centric prototype aligner (CCPA). The CDD, extended from conditional domain adversarial networks in classifier tasks, is effective and robust in handling complex cross-modality biomedical images. The CCPA, improved from the graph-induced prototype alignment mechanism in cross-domain object detection, can exploit precise instance-level features through an elaborate prototype representation. In addition, it can address the negative effect of class imbalance via entropy-based loss. Extensive experiments on a public benchmark for the cardiac substructure segmentation task demonstrate that our method significantly improves performance on the target domain. INDEX TERMS Biomedical image segmentation, cross-modality learning, unsupervised domain adaptation, category-centric prototype aligner.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Unsupervised Domain Adaptation Network With Category-Centric Prototype Aligner for Biomedical Image Segmentation

Gong

Sun

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

Source data‐free domain adaptation of object detector through domain‐specific perturbation

Xiong

Zhang

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

The current unsupervised cross‐domain detection methods need source domain data to retrain the detection model in target domain. However, the source domain data may be unavailable due to privacy, decentralization, or computation resource restrictions. A natural idea is to optimize the parameters of the source domain model by self‐supervised learning based on pseudo labels. We propose another approach from the viewpoint of noise perturbation without pseudo‐labeling. It can be assumed that the source and target domains are actually derived from a domain invariant space through domain‐specific perturbations, respectively. A super target domain can be constructed by augmenting more target domain perturbations to the target domain images. The optimal direction of the target domain to the domain invariant space can be approximated as the alignment direction from the super target domain to the target domain. Based on this idea, we propose a novel method called SOAP (SOurce data‐free domain Adaptation through domain Perturbation) which can remove domain perturbation from the target domain. The image‐level, instance‐level, and category consistency regularizations based on Mean Teacher structure are proposed to learn the correct alignment direction. Specifically, the category consistency can also further improve the classification accuracy. Extensive experiments on multiple domain adaptation scenarios demonstrate that SOAP achieves better performance surpassing the baseline (Faster R‐CNN) and multiple state‐of‐the‐art domain adaptation methods which need to access source domain data.

show abstract

A Review of University Research Development in Vietnam from 1986 to 2019

Nguyen

2020

Higher Education in Market-Oriented Socialist Vietnam

View full text Add to dashboard Cite

This paper investigates the impact of breast density distribution on the generalization performance of deep-learning models on mammography images using the VinDr-Mammo dataset. We explore the use of domain adaptation techniques, specifically Domain Adaptive Object Detection (DAOD) with the Noise Latent Transferability Exploration (NLTE) framework, to improve model performance across breast densities under noisy labeling circumstances. We propose a robust augmentation framework to bridge the domain gap between the source and target inside a dataset. Our results show that DAOD-based methods, along with the proposed augmentation framework, can improve the generalization performance of deep-learning models (+5 % overall mAP improvement approximately in our experimental results compared to commonly used detection models). This paper highlights the importance of domain adaptation techniques in medical imaging, particularly in the context of breast density distribution, which is critical in mammography screening.

show abstract

Cross-Domain Detection via Graph-Induced Prototype Alignment

Cited by 186 publications

References 32 publications

Unsupervised Domain Adaptation Network With Category-Centric Prototype Aligner for Biomedical Image Segmentation

Unsupervised Domain Adaptation Network With Category-Centric Prototype Aligner for Biomedical Image Segmentation

Source data‐free domain adaptation of object detector through domain‐specific perturbation

A Review of University Research Development in Vietnam from 1986 to 2019

Contact Info

Product

Resources

About