Domain Generalization On Pacs 2

评估指标

Average Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
SIMPLE+	99.0	SIMPLE: Specialized Model-Sample Matching for Domain Generalization	-
PromptStyler (CLIP, ViT-L/14)	98.6	PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
GMDG (RegNetY-16GF, SWAD)	97.9	Rethinking Multi-domain Generalization with A General Learning Objective
D-Triplet(RegNetY-16GF)	97.6	Domain-aware Triplet loss in Domain Generalization
MoA (OpenCLIP, ViT-B/16)	97.4	Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters
GMDG (e RegNetY-16GF)	97.3	Rethinking Multi-domain Generalization with A General Learning Objective
PromptStyler (CLIP, ViT-B/16)	97.2	PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
SPG (CLIP, ViT-B/16)	97.0	Soft Prompt Generation for Domain Generalization
CAR-FT (CLIP, ViT-B/16)	96.8	Context-Aware Robust Fine-Tuning	-
MIRO (RegNetY-16GF, SWAD)	96.8	Domain Generalization by Mutual-Information Regularization with Pre-trained Models
VL2V-SD (CLIP, ViT-B/16)	96.68	Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
SEDGE+	96.1	Domain Generalization using Pretrained Models without Fine-tuning	-
Ensemble of Averages (RegNetY-16GF)	95.8	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
UniDG + CORAL + ConvNeXt-B	95.6	Towards Unified and Effective Domain Generalization
CADG	94.6	CADG: A Model Based on Cross Attention for Domain Generalization	-
Ensemble of Averages (ResNeXt-50 32x4d)	93.2	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
PromptStyler (CLIP, ResNet-50)	93.2	PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
SPG (CLIP, ResNet-50)	92.8	Soft Prompt Generation for Domain Generalization
EoQ (ResNet-50)	90.7	QT-DoG: Quantization-aware Training for Domain Generalization
Model Ratatouille	90.5	Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization

0 of 133 row(s) selected.