4 datasets found

The Image-CLEF dataset is a benchmark dataset for visual domain adaptation. It contains 600 images from three domains.

The Office-Home dataset is a visual domain adaptation task, where the goal is to adapt a model trained in a source domain to a target domain with different distributions.

Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Most of DA methods focus on enhancing feature transferability...

VisDA2017 is a popular synthetic-to-real domain adaptation benchmark, which consists of 150k synthetic and 55k real images from 12 categories.