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 Office Home

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
MIRO (ResNet-50, SWAD)72.4Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Fishr (ResNet-50)68.2Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization-
GMDG (ResNet-50, SWAD)72.5Rethinking Multi-domain Generalization with A General Learning Objective
PromptStyler (CLIP, ResNet-50)73.6PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
GMoE-S/1674.2Sparse Mixture-of-Experts are Domain Generalizable Learners-
WAKD (DeiT-Ti)70.5Weight Averaging Improves Knowledge Distillation under Domain Shift
PromptStyler (CLIP, ViT-B/16)83.6PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
AdaClust (ResNet-50, SWAD)69.4Adaptive Methods for Aggregated Domain Generalization
PCL (swad+resnet50)71.6PCL: Proxy-Based Contrastive Learning for Domain Generalization
MIRO (RegNetY-16GF, SWAD)83.3Domain Generalization by Mutual-Information Regularization with Pre-trained Models
UniDG + CORAL + ConvNeXt-B88.9Towards Unified and Effective Domain Generalization-
AdaClust (ResNet-50)67.7Adaptive Methods for Aggregated Domain Generalization
CADG79.9CADG: A Model Based on Cross Attention for Domain Generalization-
SEDGE79.9Domain Generalization using Pretrained Models without Fine-tuning-
SagNet (ResNet-18)62.34Reducing Domain Gap by Reducing Style Bias
Ensemble of Averages (RegNetY-16GF)83.9Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
SWAD (ResNet-50)70.6SWAD: Domain Generalization by Seeking Flat Minima
DADG (ResNet-18)62.22Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation
GMDG (ResNet-50)70.7Rethinking Multi-domain Generalization with A General Learning Objective
SPG (CLIP, ResNet-50)73.8Soft Prompt Generation for Domain Generalization
0 of 45 row(s) selected.