HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Domain Generalization On Terraincognita

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

模型名称
Average Accuracy
Paper TitleRepository
SIMPLE57.6SIMPLE: Specialized Model-Sample Matching for Domain Generalization
MoA (OpenCLIP, ViT-B/16)52.8Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters-
GMoE-S/1648.5Sparse Mixture-of-Experts are Domain Generalizable Learners-
EOQ (ResNet-50)53.2QT-DoG: Quantization-aware Training for Domain Generalization
Fishr(ResNet-50)47.4Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization-
GMDG (ResNet-50)51.1Rethinking Multi-domain Generalization with A General Learning Objective
AdaClust (ResNet-50)48.1Adaptive Methods for Aggregated Domain Generalization
SIMPLE+59.0SIMPLE: Specialized Model-Sample Matching for Domain Generalization
MIRO (ResNet-50, SWAD)52.9Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Model Ratatouille52Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
UniDG + CORAL + ConvNeXt-B69.6Towards Unified and Effective Domain Generalization-
SWAD (ResNet-50)50.0SWAD: Domain Generalization by Seeking Flat Minima
SEDGE+56.8Domain Generalization using Pretrained Models without Fine-tuning-
CADG55.7CADG: A Model Based on Cross Attention for Domain Generalization-
Ensemble of Averages (ResNet-50)52.3Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
SEDGE56.8Domain Generalization using Pretrained Models without Fine-tuning-
GMDG (RegNetY-16GF, SWAD)65Rethinking Multi-domain Generalization with A General Learning Objective
GMDG (RegNetY-16GF)60.7Rethinking Multi-domain Generalization with A General Learning Objective
Ensemble of Averages (RegNetY-16GF)61.1Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
VL2V-SD (CLIP, ViT-B/16)58.54Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
0 of 30 row(s) selected.