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 151175 of 188 papers

TitleStatusHype
A Comparison of Strategies for Source-Free Domain AdaptationCode0
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
SSDA: Secure Source-Free Domain AdaptationCode0
CNG-SFDA:Clean-and-Noisy Region Guided Online-Offline Source-Free Domain AdaptationCode0
Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion AdaptationCode0
A3: Active Adversarial Alignment for Source-Free Domain AdaptationCode0
Variational Model Perturbation for Source-Free Domain AdaptationCode0
When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse WeatherCode0
SemEval-2021 Task 10: Source-Free Domain Adaptation for Semantic ProcessingCode0
SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal ConsistencyCode0
Self-training solutions for the ICCV 2023 GeoNet ChallengeCode0
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
Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain AdaptationCode0
Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation FrameworkCode0
Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain AdaptationCode0
Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain AdaptationCode0
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain AdaptationCode0
Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive DistillationCode0
Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-PromptingCode0
Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene SegmentationCode0
A Curriculum-style Self-training Approach for Source-Free Semantic SegmentationCode0
RAIN: RegulArization on Input and Network for Black-Box Domain AdaptationCode0
Show:102550
← PrevPage 7 of 8Next →

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