Domain Generalization On Vlcs

Metrics

Average Accuracy

Results

Performance results of various models on this benchmark

Model Name	Average Accuracy	Paper Title	Repository
VNE (ResNet-50, SWAD)	79.7	VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution	-
SIMPLE	79.9	SIMPLE: Specialized Model-Sample Matching for Domain Generalization
MIRO (RegNetY-16GF, SWAD)	81.7	Domain Generalization by Mutual-Information Regularization with Pre-trained Models	-
CAR-FT (CLIP, ViT-B/16)	85.5	Context-Aware Robust Fine-Tuning	-
Fishr (ResNet-50)	78.2	Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization	-
GMDG (ResNet-50)	79.2	Rethinking Multi-domain Generalization with A General Learning Objective	-
DADG (AlexNet)	74.46	Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation	-
MoA (OpenCLIP, ViT-B/16)	83.1	Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters	-
Ensemble of Averages (RegNetY-16GF)	81.1	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization	-
SEDGE+	82.2	Domain Generalization using Pretrained Models without Fine-tuning	-
AdaClust (ResNet-50)	78.9	Adaptive Methods for Aggregated Domain Generalization	-
PromptStyler (CLIP, ResNet-50)	82.3	PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization	-
AdaClust (ResNet-50, SWAD)	79.6	Adaptive Methods for Aggregated Domain Generalization	-
GMDG (RegNetY-16GF)	82.4	Rethinking Multi-domain Generalization with A General Learning Objective	-
SWAD (ResNet-50)	79.1	SWAD: Domain Generalization by Seeking Flat Minima	-
VL2V-SD (CLIP, ViT-B/16)	83.25	Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification	-
SEDGE	79.8	Domain Generalization using Pretrained Models without Fine-tuning	-
UniDG + CORAL + ConvNeXt-B	84.5	Towards Unified and Effective Domain Generalization	-
Ensemble of Averages (ResNeXt-50 32x4d)	80.4	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization	-
D-Triplet(RegNetY-16GF)	82.9	Domain-aware Triplet loss in Domain Generalization	-

0 of 37 row(s) selected.