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 101–125 of 188 papers

TitleStatusHype
SSDA: Secure Source-Free Domain AdaptationCode0
RAIN: RegulArization on Input and Network for Black-Box Domain AdaptationCode0
Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain AdaptationCode0
Variational Model Perturbation for Source-Free Domain AdaptationCode0
What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood ContextCode0
When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse WeatherCode0
AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation—0
Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation—0
Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation—0
Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation—0
Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation—0
Semantic Image Segmentation: Two Decades of Research—0
Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective—0
Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation—0
Semi-Supervised Transfer Boosting (SS-TrBoosting)—0
SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterization—0
Generating Reliable Pixel-Level Labels for Source Free Domain Adaptation—0
Adaptive Adversarial Network for Source-Free Domain Adaptation—0
Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognition—0
Active Source Free Domain Adaptation—0
Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples—0
FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions—0
Feed-Forward Latent Domain Adaptation—0
Feed-Forward Source-Free Domain Adaptation via Class Prototypes—0
Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data—0
Show:102550
← PrevPage 5 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