Domain Adaptation On Svhn To Mnist

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
Mean teacher	99.18	Self-ensembling for visual domain adaptation
DFA-MCD	98.9	Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment
SHOT	98.9	Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
FAMCD	98.76	Unsupervised domain adaptation using feature aligned maximum classifier discrepancy
DFA-ENT	98.2	Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment
CyCleGAN (Light-weight Calibrator)	97.5	Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation
MCD	95.8	Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
PFA	93.9	Progressive Feature Alignment for Unsupervised Domain Adaptation
MSTN	93.3	Learning Semantic Representations for Unsupervised Domain Adaptation
FACT	90.6	FACT: Federated Adversarial Cross Training
CYCADA	90.4	CyCADA: Cycle-Consistent Adversarial Domain Adaptation
CDAN	89.2	Conditional Adversarial Domain Adaptation
ADDN	80.1	Adversarial Discriminative Domain Adaptation
SBADA	76.1	From source to target and back: symmetric bi-directional adaptive GAN

0 of 14 row(s) selected.

Domain Adaptation On Svhn To Mnist | SOTA | HyperAI