Domain Generalization On Domainnet

평가 지표

Average Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Average Accuracy	Paper Title	Repository
SWAD (ResNet-50)	46.5	SWAD: Domain Generalization by Seeking Flat Minima
MIRO (RegNetY-16GF, SWAD)	60.7	Domain Generalization by Mutual-Information Regularization with Pre-trained Models
PromptStyler (CLIP, ViT-L/14)	65.5	PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
GMDG (RegNetY-16GF, SWAD)	61.3	Rethinking Multi-domain Generalization with A General Learning Objective
Hybrid-SF-MoE	52.0	Sparse Mixture-of-Experts are Domain Generalizable Learners	-
Meta-DMoE (ResNet-50)	44.2	Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts
CADG	51.6	CADG: A Model Based on Cross Attention for Domain Generalization	-
SPG (CLIP, ViT-B/16)	60.1	Soft Prompt Generation for Domain Generalization
GMDG (RegNetY-16GF)	54.6	Rethinking Multi-domain Generalization with A General Learning Objective
DMG (ResNet-50)	43.63	Learning to Balance Specificity and Invariance for In and Out of Domain Generalization
VL2V-SD (CLIP, ViT-B/16)	62.79	Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
SPG (CLIP, ResNet-50)	50.1	Soft Prompt Generation for Domain Generalization
GMDG (ResNet-50, SWAD)	47.3	Rethinking Multi-domain Generalization with A General Learning Objective
SIMPLE+	61.9	SIMPLE: Specialized Model-Sample Matching for Domain Generalization
SEDGE+	54.7	Domain Generalization using Pretrained Models without Fine-tuning	-
SIMPLE	49.2	SIMPLE: Specialized Model-Sample Matching for Domain Generalization
Ensemble of Averages (RegNetY-16GF)	60.9	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
DDG	46.93	Dynamic Domain Generalization
Ensemble of Averages (ResNet-50)	47.4	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
MetaReg (ResNet-50)	43.62	Learning to Balance Specificity and Invariance for In and Out of Domain Generalization

0 of 36 row(s) selected.