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

Spatially Attentive Output Layer for Image Classification

The proposed SAOL improves the performances of representative architectures for various tasks, with almost the same computational cost. Moreover, additional self-supervision losses specifically designed for SAOL also improve the performances further.

Data and Resources

Cite this as

Ildoo Kim, Woonhyuk Baek, Sungwoong Kim (2024). Dataset: Spatially Attentive Output Layer for Image Classification. https://doi.org/10.57702/zlyrjoj3

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2004.07570
Author Ildoo Kim
More Authors
Woonhyuk Baek
Sungwoong Kim