Source-Free Domain Adaptation
7개 벤치마크 · 논문 224편 · 이 태스크의 논문 보기 →
Benchmarks
VisDA-2017
PACS
Cityscapes to ACDC
VIPER-to-Cityscapes
GTA5 to Cityscapes
SYNTHIA-to-Cityscapes
Most implemented
Upcycling Models under Domain and Category Shift
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting
Papers
Dual Co-Train: Cross-Dataset Ultrasound Tongue Segmentation Under Extreme Data Scarcity
Ultrasound tongue contour segmentation remains challenging under cross-dataset domain shift, where limited annotations, probe variability, and acquisition noise often degrade model generalization. We present a source-fre…
Source-Free Domain AdaptationTestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model
Test-Time Domain Adaptation (TTDA) aims to adapt Deep Neural Networks to distribution shifts using only streaming, unlabeled test data in real time. Current methods for semantic segmentation tasks suffer from critical li…
Source-Free Domain AdaptationSemantic SegmentationInstance SegmentationBrainRiem: Riemannian Prototype Learning for Source-Free Cross-Site Brain Network Diagnosis
Multi-site functional MRI (fMRI) studies are essential for robust neuropsychiatric diagnosis yet suffer severe domain shifts from scanner heterogeneity, demographics, and site-specific acquisition protocols. Traditional …
Source-Free Domain AdaptationGRAPH DOMAIN ADAPTATIONTemporal-Spectral Alignment with Frequency Adaptation for Source-Free Time-Series Adaptation
The goal of source-free domain adaptation (SFDA) for time-series data is to transfer knowledge from a pre-trained source model to an unlabeled target domain without requiring access to source data, while addressing featu…
Source-Free Domain AdaptationRethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model
Source-Free Domain Adaptation (SFDA) adapts source models to target domains without accessing source data, addressing privacy and transmission issues. However, existing methods still initialize from a source pre-trained …
Source-Free Domain AdaptationFoundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding
Source-free domain adaptation (SFDA) provides a practical solution to cross-subject EEG decoding by adapting source-pretrained models to unlabeled target domains without accessing source data. However, existing SFDA meth…
Source-Free Domain AdaptationKnowledge DistillationDomain GeneralizationEmotion Recognition