Domain Adaptation on SVHN-to-MNIST

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

#	Model↕	Accuracy▼	Augmentations	Paper	Date↕	Code
1	Mean teacher	99.18	No	Self-ensembling for visual domain adaptation	2017-06-16	Code
2	SHOT	98.9	No	Do We Really Need to Access the Source Data? Sou...	2020-02-20	Code
3	DFA-MCD	98.9	No	Discriminative Feature Alignment: Improving Tran...	2020-06-23	Code
4	FAMCD	98.76	No	-	-	-
5	DFA-ENT	98.2	No	Discriminative Feature Alignment: Improving Tran...	2020-06-23	Code
6	CyCleGAN (Light-weight Calibrator)	97.5	No	Light-weight Calibrator: a Separable Component f...	2019-11-28	Code
7	MCD	95.8	No	Maximum Classifier Discrepancy for Unsupervised ...	2017-12-07	Code
8	PFA	93.9	No	Progressive Feature Alignment for Unsupervised D...	2018-11-21	-
9	MSTN	93.3	No	-	-	Code
10	FACT	90.6	No	FACT: Federated Adversarial Cross Training	2023-06-01	Code
11	CYCADA	90.4	No	CyCADA: Cycle-Consistent Adversarial Domain Adap...	2017-11-08	Code
12	CDAN	89.2	No	Conditional Adversarial Domain Adaptation	2017-05-26	Code
13	ADDN	80.1	No	Adversarial Discriminative Domain Adaptation	2017-02-17	Code
14	SBADA	76.1	No	From source to target and back: symmetric bi-dir...	2017-05-24	-