HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Domain Generalization On Domainnet

Metriken

Average Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
PromptStyler (CLIP, ViT-L/14)65.5PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
VDPG (CLIP, ViT-L/14)65.2Adapting to Distribution Shift by Visual Domain Prompt Generation
VL2V-SD (CLIP, ViT-B/16)62.79Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
MoA (OpenCLIP, ViT-B/16)62.7Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters
CAR-FT (CLIP, ViT-B/16)62.5Context-Aware Robust Fine-Tuning
SIMPLE+61.9SIMPLE: Specialized Model-Sample Matching for Domain Generalization
GMDG (RegNetY-16GF, SWAD)61.3Rethinking Multi-domain Generalization with A General Learning Objective
Ensemble of Averages (RegNetY-16GF)60.9Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
MIRO (RegNetY-16GF, SWAD)60.7Domain Generalization by Mutual-Information Regularization with Pre-trained Models
SPG (CLIP, ViT-B/16)60.1Soft Prompt Generation for Domain Generalization
VDPG (CLIP, ViT-B/16)59.8Adapting to Distribution Shift by Visual Domain Prompt Generation
UniDG + CORAL + ConvNeXt-B59.5Towards Unified and Effective Domain Generalization
PromptStyler (CLIP, ViT-B/16)59.4PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
SEDGE+54.7Domain Generalization using Pretrained Models without Fine-tuning
GMDG (RegNetY-16GF)54.6Rethinking Multi-domain Generalization with A General Learning Objective
Ensemble of Averages (ResNeXt-50 32x4d)54.6Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
Hybrid-SF-MoE52.0Sparse Mixture-of-Experts are Domain Generalizable Learners
CADG51.6CADG: A Model Based on Cross Attention for Domain Generalization
SPG (CLIP, ResNet-50)50.1Soft Prompt Generation for Domain Generalization
PromptStyler (CLIP, ResNet-50)49.5PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
0 of 36 row(s) selected.