Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Methodology
/
Domain Adaptation
/
MNIST-to-USPS
Domain Adaptation on MNIST-to-USPS
Metric: Accuracy (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
#
Model
↕
Accuracy
▼
Augmentations
Paper
Date
↕
Code
1
FACT
98.8
No
FACT: Federated Adversarial Cross Training
2023-06-01
Code
2
FAMCD
98.72
No
-
-
-
3
DFA-MCD
98.6
No
Discriminative Feature Alignment: Improving Tran...
2020-06-23
Code
4
Mean teacher
98.26
No
Self-ensembling for visual domain adaptation
2017-06-16
Code
5
DRANet
98.2
No
DRANet: Disentangling Representation and Adaptat...
2021-03-24
Code
6
SHOT
98
No
Do We Really Need to Access the Source Data? Sou...
2020-02-20
Code
7
DFA-ENT
97.9
No
Discriminative Feature Alignment: Improving Tran...
2020-06-23
Code
8
CyCleGAN (Light-weight Calibrator)
97.1
No
Light-weight Calibrator: a Separable Component f...
2019-11-28
Code
9
3CATN
96.1
No
Cycle-consistent Conditional Adversarial Transfe...
2019-09-17
Code
10
rRevGrad+CAT
96
No
Cluster Alignment with a Teacher for Unsupervise...
2019-03-24
Code
11
DeepJDOT
95.7
No
DeepJDOT: Deep Joint Distribution Optimal Transp...
2018-03-27
Code
12
SRDA (RAN)
94.76
No
Learning Smooth Representation for Unsupervised ...
2019-05-26
Code
13
MCD
93.8
No
Maximum Classifier Discrepancy for Unsupervised ...
2017-12-07
Code
14
ADDN
90.1
No
Adversarial Discriminative Domain Adaptation
2017-02-17
Code