TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers

Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency.

Data and Resources

Cite this as

Hyeong Kyu Choi, Joonmyung Choi, Hyunwoo J. Kim (2024). Dataset: TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers. https://doi.org/10.57702/vwwj19a7

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.2210.07562
Author Hyeong Kyu Choi
More Authors
Joonmyung Choi
Hyunwoo J. Kim
Homepage https://github.com/mlvlab/TokenMixup