Domain Adaptation BenchmarksΒΆ

Note

Site currently under construction 🚧

This page will contain updates about domain adaptation benchmarks and the papers currently being state of the art for each particular dataset.

Digit BenchmarksΒΆ

Sour ceTa rget MNIS TMNI ST-M Synt hSVH N MNIS TSVH N SVHN MNIS T MNIS TUSP S USPS MNIS T
SA 56.9 0 86.4 4 ? 59.3 2 ? ?
DANN 76.6 6 91.0 9 ? 73.8 5 ? ?
CoGA N ? ? ? ? 91.2 89.1
DRCN ? ? 40.0 5 81.9 7 91.8 0 73.6 7
DSN 83.2 91.2 ? 82.7 ? ?
DTN ? ? 90.6 6 79.7 2 ? ?
Pixe lDA 98.2 ? ? ? 95.9 ?
ADDA ? ? ? 76.0 89.4 90.1
UNIT ? ? ? 90.5 3 95.9 7 93.5 8
GenT oAda pt ? ? ? 92.4 95.3 90.8
SBAD A-GA N 99.4 ? 61.1 76.1 97.6 95.0
DAas soc 89.4 7 91.8 6 ? 97.6 0 ? ?
CyCA DA ? ? ? 90.4 95.6 96.5
I2I ? ? ? 92.1 95.1 92.2
DIRT -T 98.7 ? 76.5 99.4 ? ?
Deep JDOT 92.4 ? ? 96.7 95.7 96.4

Source: Awesome Transfer Learning reading list

VisDA Benchmark and TASK-CVΒΆ