HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

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
SIMPLE+99.0SIMPLE: Specialized Model-Sample Matching for Domain Generalization
PromptStyler (CLIP, ViT-L/14)98.6PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
GMDG (RegNetY-16GF, SWAD)97.9Rethinking Multi-domain Generalization with A General Learning Objective
D-Triplet(RegNetY-16GF)97.6Domain-aware Triplet loss in Domain Generalization
MoA (OpenCLIP, ViT-B/16)97.4Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters
GMDG (e RegNetY-16GF)97.3Rethinking Multi-domain Generalization with A General Learning Objective
PromptStyler (CLIP, ViT-B/16)97.2PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
SPG (CLIP, ViT-B/16)97.0Soft Prompt Generation for Domain Generalization
CAR-FT (CLIP, ViT-B/16)96.8Context-Aware Robust Fine-Tuning
MIRO (RegNetY-16GF, SWAD)96.8Domain Generalization by Mutual-Information Regularization with Pre-trained Models
VL2V-SD (CLIP, ViT-B/16)96.68Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
SEDGE+96.1Domain Generalization using Pretrained Models without Fine-tuning
Ensemble of Averages (RegNetY-16GF)95.8Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
UniDG + CORAL + ConvNeXt-B95.6Towards Unified and Effective Domain Generalization
CADG94.6CADG: A Model Based on Cross Attention for Domain Generalization
Ensemble of Averages (ResNeXt-50 32x4d)93.2Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
PromptStyler (CLIP, ResNet-50)93.2PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
SPG (CLIP, ResNet-50)92.8Soft Prompt Generation for Domain Generalization
EoQ (ResNet-50)90.7QT-DoG: Quantization-aware Training for Domain Generalization
Model Ratatouille90.5Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
0 of 133 row(s) selected.