Infinite Class Mixup

Mixup is a widely adopted strategy for training deep networks, where additional samples are augmented by interpolating inputs and labels of training pairs. Mixup has shown to improve classification performance, network calibration, and out-of-distribution generalisation.

Data and Resources

Cite this as

Thomas Mensink, Pascal Mettes (2024). Dataset: Infinite Class Mixup. https://doi.org/10.57702/spph2gcr

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.2305.10293
Author Thomas Mensink
More Authors
Pascal Mettes
Homepage https://github.com/psmmettes/icm