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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 188 papers

TitleStatusHype
Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety—0
Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain AdaptationCode0
What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood ContextCode0
Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data—0
Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion AdaptationCode0
Semi-Supervised Transfer Boosting (SS-TrBoosting)—0
Knowledge-Data Fusion Based Source-Free Semi-Supervised Domain Adaptation for Seizure Subtype Classification—0
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation—0
Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptation—0
Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation FrameworkCode0
Day-Night Adaptation: An Innovative Source-free Adaptation Framework for Medical Image Segmentation—0
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement—0
A3: Active Adversarial Alignment for Source-Free Domain AdaptationCode0
SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal ConsistencyCode0
Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classification—0
EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse PrinciplesCode0
FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions—0
Source -Free Domain Adaptation for Speaker Verification in Data-Scarce Languages and Noisy Channels—0
Evidentially Calibrated Source-Free Time-Series Domain Adaptation with Temporal Imputation—0
Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum LearningCode0
SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural NetworkCode0
Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-TrainingCode0
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for HistologyCode0
Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions—0
When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse WeatherCode0
Show:102550
← PrevPage 4 of 8Next →
All datasetsVisDA-2017PACSCityscapes to ACDCCityscapes to Dark Zurich

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RCLAccuracy93.2—Unverified
2SFDA2++Accuracy89.6—Unverified
3SPMAccuracy89.4—Unverified
4SFDA2Accuracy88.1—Unverified
5C-SFDAAccuracy87.8—Unverified
6DaCAccuracy87.3—Unverified
7SHOT++Accuracy87.3—Unverified
8NRCAccuracy85.9—Unverified
9G-SFDAAccuracy85.4—Unverified
10SHOTAccuracy82.9—Unverified
#ModelMetricClaimedVerifiedStatus
1SPMAverage Accuracy86.7—Unverified
2DRAAverage Accuracy84—Unverified
3NELAverage Accuracy72.4—Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU69.1—Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU53.6—Unverified