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 51100 of 188 papers

TitleStatusHype
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling TransferCode1
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation TransformerCode1
Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance InsightsCode1
Balancing Discriminability and Transferability for Source-Free Domain AdaptationCode1
Sign Segmentation with Changepoint-Modulated Pseudo-LabellingCode1
Tent: Fully Test-time Adaptation by Entropy MinimizationCode1
GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain AdaptationCode1
SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging AnalysisCode1
Generalized Source-free Domain AdaptationCode1
SF(DA)^2: Source-free Domain Adaptation Through the Lens of Data AugmentationCode1
SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous EnvironmentsCode1
Transformer-Based Source-Free Domain AdaptationCode1
1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection TrackCode0
A3: Active Adversarial Alignment for Source-Free Domain AdaptationCode0
A Comparison of Strategies for Source-Free Domain AdaptationCode0
Agile Multi-Source-Free Domain AdaptationCode0
Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion AdaptationCode0
CNG-SFDA:Clean-and-Noisy Region Guided Online-Offline Source-Free Domain AdaptationCode0
Rethinking the Role of Pre-Trained Networks in Source-Free Domain AdaptationCode0
Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain AdaptationCode0
DDFP: Data-dependent Frequency Prompt for Source Free Domain Adaptation of Medical Image SegmentationCode0
De-Confusing Pseudo-Labels in Source-Free Domain AdaptationCode0
Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target DataCode0
Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled DataCode0
EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse PrinciplesCode0
Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum LearningCode0
FACT: Federated Adversarial Cross TrainingCode0
Few-shot Fine-tuning is All You Need for Source-free Domain AdaptationCode0
A Curriculum-style Self-training Approach for Source-Free Semantic SegmentationCode0
Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene SegmentationCode0
Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-PromptingCode0
Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive DistillationCode0
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain AdaptationCode0
Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain AdaptationCode0
Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain AdaptationCode0
Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation FrameworkCode0
Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain AdaptationCode0
Self-training solutions for the ICCV 2023 GeoNet ChallengeCode0
SemEval-2021 Task 10: Source-Free Domain Adaptation for Semantic ProcessingCode0
SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal ConsistencyCode0
Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain AdaptationCode0
SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain AdaptationCode0
Source-Free Domain Adaptation for Question Answering with Masked Self-trainingCode0
Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-TrainingCode0
Source-Free Domain Adaptation for SSVEP-based Brain-Computer InterfacesCode0
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for HistologyCode0
Source-Free Domain Adaptation via Distribution EstimationCode0
Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic SegmentationCode0
SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural NetworkCode0
SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image SegmentationCode0
Show:102550
← PrevPage 2 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RCLAccuracy93.2Unverified
2SFDA2++Accuracy89.6Unverified
3SPMAccuracy89.4Unverified
4SFDA2Accuracy88.1Unverified
5C-SFDAAccuracy87.8Unverified
6DaCAccuracy87.3Unverified
7SHOT++Accuracy87.3Unverified
8NRCAccuracy85.9Unverified
9G-SFDAAccuracy85.4Unverified
10SHOTAccuracy82.9Unverified
#ModelMetricClaimedVerifiedStatus
1SPMAverage Accuracy86.7Unverified
2DRAAverage Accuracy84Unverified
3NELAverage Accuracy72.4Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU69.1Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU53.6Unverified