Domain Adaptation On Office Home

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
CMKD	89.0	Unsupervised Domain Adaption Harnessing Vision-Language Pre-training
DAOD	69.8	Open Set Domain Adaptation: Theoretical Bound and Algorithm
FixBi	72.7	FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
RCL	90.0	Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum Learning
PGA (ViT-B/16)	85.1	Enhancing Domain Adaptation through Prompt Gradient Alignment
SWG	92.3	Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance
SHOT	71.8	Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
MEDM	69.5	Entropy Minimization vs. Diversity Maximization for Domain Adaptation
MEDA (ResNet50)	67.6	Transfer Learning with Dynamic Distribution Adaptation
CoVi	73.1	Contrastive Vicinal Space for Unsupervised Domain Adaptation
GSDE	73.6	Gradual Source Domain Expansion for Unsupervised Domain Adaptation
MCC+NWD	72.6	Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
PGA (ViT-L/14)	89.4	Enhancing Domain Adaptation through Prompt Gradient Alignment
PMTrans	89.0	Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective	-
CDTrans (DeiT-B)	80.5	CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
BIWAA	71.5	Backprop Induced Feature Weighting for Adversarial Domain Adaptation with Iterative Label Distribution Alignment
ELS	84.6	Free Lunch for Domain Adversarial Training: Environment Label Smoothing
MIC	86.2	MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
SDAT (ViT-B/16)	84.3	A Closer Look at Smoothness in Domain Adversarial Training
EvoADA	73.9	On Evolving Attention Towards Domain Adaptation	-

0 of 29 row(s) selected.