You're currently viewing an old version of this dataset. To see the current version, click here.

Office-Caltech10

Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Most of DA methods focus on enhancing feature transferability through domain-invariance learning. However, source-learned discriminability itself might be tailored to be biased and unsafely transferable by spurious correlations, i.e., part of source-speciļ¬c features are correlated with category labels.

Data and Resources

This dataset has no data

Cite this as

Z. Deng, Y. Luo, J. Zhu (2024). Dataset: Office-Caltech10. https://doi.org/10.57702/gds3bkkt

Private DOI This DOI is not yet resolvable.
It is available for use in manuscripts, and will be published when the Dataset is made public.

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2404.06599
Citation
  • https://doi.org/10.1109/TKDE.2021.3119185
  • https://doi.org/10.48550/arXiv.2011.03737
Author Z. Deng
More Authors
Y. Luo
J. Zhu
Homepage https://cs.nyu.edu/~ylclab/research/datasets/office-31.html