SOTAVerified

Single-Source Domain Generalization

In this task a model is trained in a single source domain and then it is tested in a number of target domains

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 48 papers

TitleStatusHype
Dealing with the Evil Twins: Improving Random Augmentation by Addressing Catastrophic Forgetting of Diverse Augmentations—0
Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain GeneralizationCode0
PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization—0
Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image SegmentationCode2
Mono2D: A Trainable Monogenic Layer for Robust Knee Cartilage Segmentation on Out-of-Distribution 2D Ultrasound Data—0
Color-Quality Invariance for Robust Medical Image SegmentationCode0
Avoiding Shortcuts: Enhancing Channel-Robust Specific Emitter Identification via Single-Source Domain GeneralizationCode2
Rethinking domain generalization in medical image segmentation: One image as one domain—0
Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification—0
TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction—0
Show:102550
← PrevPage 1 of 5Next →
All datasetsPACSDigits-five

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Crafting-Shifts(LeNet)Accuracy82.61—Unverified
2ProRandConv (LeNet)Accuracy81.35—Unverified
3CADA (LeNet)Accuracy80.56—Unverified
4MCL (LeNet)Accuracy78.82—Unverified
5MetaCNN (LeNet)Accuracy78.76—Unverified
6ABA (LeNet)Accuracy76.72—Unverified
7L2D (LeNet)Accuracy74.46—Unverified