paper-with-me

홈 › Papers

Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation

2023-08-15 · Zheang Huai, Xinpeng Ding, Yi Li, Xiaomeng Li

In the domain adaptation problem, source data may be unavailable to the target client side due to privacy or intellectual property issues. Source-free unsupervised domain adaptation (SF-UDA) aims at adapting a model trained on the source side to align the target distribution with only the source model and unlabeled target data. The source model usually produces noisy and context-inconsistent pseudo-labels on the target domain, i.e., neighbouring regions that have a similar visual appearance are annotated with different pseudo-labels. This observation motivates us to refine pseudo-labels with context relations. Another observation is that features of the same class tend to form a cluster despite the domain gap, which implies context relations can be readily calculated from feature distances. To this end, we propose a context-aware pseudo-label refinement method for SF-UDA. Specifically, a context-similarity learning module is developed to learn context relations. Next, pseudo-label revision is designed utilizing the learned context relations. Further, we propose calibrating the revised pseudo-labels to compensate for wrong revision caused by inaccurate context relations. Additionally, we adopt a pixel-level and class-level denoising scheme to select reliable pseudo-labels for domain adaptation. Experiments on cross-domain fundus images indicate that our approach yields the state-of-the-art results. Code is available at https://github.com/xmed-lab/CPR.

📄 PDF Abstract BibTeX arXiv:2308.07731

Code (3)

xmed-lab/cpr 공식 구현 pytorch
xmed-lab/dfg pytorch
zheangh/dfg pytorch

Tasks

DenoisingDomain AdaptationImage SegmentationPseudo LabelSemantic SegmentationUnsupervised 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…

Similar Papers 제목 키워드 기반

CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement

2022-05-26 · Can Zhang, Gim Hee Lee

Recent works on unsupervised domain adaptation (UDA) focus on the selection of good pseudo-labels as surrogates for the missing labels in the target data. However, source domain bias that deteriorates the pseudo-labels c…

Domain Adaptationimage-classificationImage ClassificationMissing Labels+2

Flick: Few Labels Text Classification using K-Aware Intermediate Learning in Multi-Task Low-Resource Languages

2025-06-12 · Ali Almutairi, Abdullah Alsuhaibani, Shoaib Jameel, Usman Naseem 외

Training deep learning networks with minimal supervision has gained significant research attention due to its potential to reduce reliance on extensive labelled data. While self-training methods have proven effective in …

Domain AdaptationPseudo Labeltext-classificationText Classification

ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models

2026-02-21 · Zefang Liu, Chenyang Zhu, Sangwoo Cho, Shi-Xiong Zhang arxiv

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, …

Speech Recognition

Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning

2025-08-01 · Yingxu Wang, Mengzhu Wang, Zhichao Huang, Suyu Liu 외 arxiv

Graph Domain Adaptation (GDA) facilitates knowledge transfer from labeled source graphs to unlabeled target graphs by learning domain-invariant representations, which is essential in applications such as molecular proper…

Molecular Property PredictionGRAPH DOMAIN ADAPTATION

3D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinement

2025-10-17 · Xiaoxu Xu, Xuexun Liu, Jinlong Li, Yitian Yuan 외 arxiv

3D weakly supervised semantic segmentation (3D WSSS) aims to achieve semantic segmentation by leveraging sparse or low-cost annotated data, significantly reducing reliance on dense point-wise annotations. Previous works …

Semantic Segmentation