Skip to yearly menu bar Skip to main content


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

Hyeong Kyu Choi · Joonmyung Choi · Hyunwoo Kim

Hall J (level 1) #632

Keywords: [ Vision transformer ] [ mixup ] [ Data Augmentation ]


Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation and are especially burdensome for parameter-heavy transformer models. To this end, we propose TokenMixup, an efficient attention-guided token-level data augmentation method that aims to maximize the saliency of a mixed set of tokens. TokenMixup provides ×15 faster saliency-aware data augmentation compared to gradient-based methods. Moreover, we introduce a variant of TokenMixup which mixes tokens within a single instance, thereby enabling multi-scale feature augmentation. Experiments show that our methods significantly improve the baseline models’ performance on CIFAR and ImageNet-1K, while being more efficient than previous methods. We also reach state-of-the-art performance on CIFAR-100 among from-scratch transformer models. Code is available at

Chat is not available.