Spatially Attentive Output Layer for Image Classification

doi:doi:10.57702/zlyrjoj3

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

Original MetadataJSON
The json representation of the dataset with its distributions based on DCAT.
Explore
- Preview
- Download

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