Domain Adaptation On Visda2017

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
CDAN	73.7	Conditional Adversarial Domain Adaptation
CRST	78.1	Confidence Regularized Self-Training
CAN	87.2	Contrastive Adaptation Network for Unsupervised Domain Adaptation
MCC+NWD	83.7	Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
SWG	92.7	Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance
PMtrans	88.8	Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective	-
FixBi	87.2	FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
SENTRY (ResNet50)	76.7	SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation
JAN	58.3	Deep Transfer Learning with Joint Adaptation Networks
SFDA2++	89.6	SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
CPGA	86.0	Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
Mean teacher	85.4	Self-ensembling for visual domain adaptation
DeepJDOT	66.9	DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
CoVi	88.5	Contrastive Vicinal Space for Unsupervised Domain Adaptation
DePT	90.7	Visual Prompt Tuning for Test-time Domain Adaptation	-
CDTrans	88.4	CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
SFDA2	88.1	SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
dSNE	86.15	d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding
MIC	92.8	MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
RCL	93.2	Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum Learning

0 of 28 row(s) selected.