2025
Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers
AAAI 2025technical
Vision transformers (ViTs) have demonstrated remarkable performance in a variety of vision tasks. Despite their promising capabilities, training a ViT requires a large amount of diverse data. Several studies empirically found that using rich data augmentations, such as Mixup, Cutmix, and random eras…