SOTAVerified

Source-Free Domain Adaptation

Source-Free Domain Adaptation (SFDA) is a domain adaptation method in machine learning and computer vision where the goal is to adapt a pre-trained model to a new, target domain without access to the source domain data. This approach is advantageous in scenarios where sharing the source data is impractical due to privacy concerns, data size, or proprietary restrictions

Papers

Showing 110 of 188 papers

TitleStatusHype
SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image SegmentationCode0
Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain AdaptationCode0
DDFP: Data-dependent Frequency Prompt for Source Free Domain Adaptation of Medical Image SegmentationCode0
Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-PromptingCode0
Learning Compositional Transferability of Time Series for Source-Free Domain Adaptation0
Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled DataCode0
Probability Distribution Alignment and Low-Rank Weight Decomposition for Source-Free Domain Adaptive Brain Decoding0
ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation0
ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Model0
Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target DataCode0
Show:102550
← PrevPage 1 of 19Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SPMAverage Accuracy86.7Unverified
2DRAAverage Accuracy84Unverified
3NELAverage Accuracy72.4Unverified