Domain Adaptation On Mnist To Usps

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
FACT	98.8	FACT: Federated Adversarial Cross Training
FAMCD	98.72	Unsupervised domain adaptation using feature aligned maximum classifier discrepancy
DFA-MCD	98.6	Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment
Mean teacher	98.26	Self-ensembling for visual domain adaptation
DRANet	98.2	DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
SHOT	98.0	Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
DFA-ENT	97.9	Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment
CyCleGAN (Light-weight Calibrator)	97.1	Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation
3CATN	96.1	Cycle-consistent Conditional Adversarial Transfer Networks
rRevGrad+CAT	96	Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
DeepJDOT	95.7	DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
SRDA (RAN)	94.76	Learning Smooth Representation for Unsupervised Domain Adaptation
MCD	93.8	Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
ADDN	90.1	Adversarial Discriminative Domain Adaptation

0 of 14 row(s) selected.

Domain Adaptation On Mnist To Usps | SOTA | HyperAI