paper-with-me

Papers

Deep Feature Registration for Unsupervised Domain Adaptation

2023-10-24 · Youshan Zhang, Brian D. Davison

While unsupervised domain adaptation has been explored to leverage the knowledge from a labeled source domain to an unlabeled target domain, existing methods focus on the distribution alignment between two domains. However, how to better align source and target features is not well addressed. In this paper, we propose a deep feature registration (DFR) model to generate registered features that maintain domain invariant features and simultaneously minimize the domain-dissimilarity of registered features and target features via histogram matching. We further employ a pseudo label refinement process, which considers both probabilistic soft selection and center-based hard selection to improve the quality of pseudo labels in the target domain. Extensive experiments on multiple UDA benchmarks demonstrate the effectiveness of our DFR model, resulting in new state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2310.16100

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationPseudo LabelUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Focus 설명 없음

Similar Papers 제목 키워드 기반

Unsupervised learning of multimodal image registration using domain adaptation with projected Earth Move's discrepancies

2020-05-28 · Mattias P. Heinrich, Lasse Hansen

Multimodal image registration is a very challenging problem for deep learning approaches. Most current work focuses on either supervised learning that requires labelled training scans and may yield models that bias towar…

Domain AdaptationImage RegistrationUnsupervised Domain Adaptation

Unsupervised learning of multimodal image registration using domain adaptation with projected Earth Mover’s discrepancies

2020-01-25 · MIDL 2019 7 · Mattias P Heinrich, Lasse Hansen

Multimodal image registration is a very challenging problem for deep learning approaches. Most current work focuses on either supervised learning that requires labelled training scans and may yield models that bias towar…

Domain AdaptationImage RegistrationUnsupervised Domain Adaptation

Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registration

2019-10-18 · Dwarikanath Mahapatra

Medical image registration is an important task in automated analysis of multi-modal images and temporal data involving multiple patient visits. Conventional approaches, although useful for different image types, are tim…

Domain AdaptationImage RegistrationMedical Image RegistrationUnsupervised Domain Adaptation

Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention Network

2022-10-09 · Lu Gan, Connor Lee, Soon-Jo Chung

This work presents a new method for unsupervised thermal image classification and semantic segmentation by transferring knowledge from the RGB domain using a multi-domain attention network. Our method does not require an…

Domain Adaptationimage-classificationImage ClassificationScene Segmentation+2

Self-Supervised 2D/3D Registration for X-Ray to CT Image Fusion

2022-10-14 · Srikrishna Jaganathan, Maximilian Kukla, Jian Wang, Karthik Shetty 외

Deep Learning-based 2D/3D registration enables fast, robust, and accurate X-ray to CT image fusion when large annotated paired datasets are available for training. However, the need for paired CT volume and X-ray images …

Domain Adaptation