Domain Generalization On Office Home

Metrics

Average Accuracy

Results

Performance results of various models on this benchmark

Model Name	Average Accuracy	Paper Title	Repository
MIRO (ResNet-50, SWAD)	72.4	Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Fishr (ResNet-50)	68.2	Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization	-
GMDG (ResNet-50, SWAD)	72.5	Rethinking Multi-domain Generalization with A General Learning Objective
PromptStyler (CLIP, ResNet-50)	73.6	PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
GMoE-S/16	74.2	Sparse Mixture-of-Experts are Domain Generalizable Learners	-
WAKD (DeiT-Ti)	70.5	Weight Averaging Improves Knowledge Distillation under Domain Shift
PromptStyler (CLIP, ViT-B/16)	83.6	PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
AdaClust (ResNet-50, SWAD)	69.4	Adaptive Methods for Aggregated Domain Generalization
PCL (swad+resnet50)	71.6	PCL: Proxy-Based Contrastive Learning for Domain Generalization
MIRO (RegNetY-16GF, SWAD)	83.3	Domain Generalization by Mutual-Information Regularization with Pre-trained Models
UniDG + CORAL + ConvNeXt-B	88.9	Towards Unified and Effective Domain Generalization	-
AdaClust (ResNet-50)	67.7	Adaptive Methods for Aggregated Domain Generalization
CADG	79.9	CADG: A Model Based on Cross Attention for Domain Generalization	-
SEDGE	79.9	Domain Generalization using Pretrained Models without Fine-tuning	-
SagNet (ResNet-18)	62.34	Reducing Domain Gap by Reducing Style Bias
Ensemble of Averages (RegNetY-16GF)	83.9	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
SWAD (ResNet-50)	70.6	SWAD: Domain Generalization by Seeking Flat Minima
DADG (ResNet-18)	62.22	Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation
GMDG (ResNet-50)	70.7	Rethinking Multi-domain Generalization with A General Learning Objective
SPG (CLIP, ResNet-50)	73.8	Soft Prompt Generation for Domain Generalization

0 of 45 row(s) selected.