← Search

Sang Woo Kim

2 accepted papers

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…

2023

How to use dropout correctly on residual networks with batch normalization

UAI 2023poster

For the stable optimization of deep neural networks, regularization methods such as dropout and batch normalization have been used in various tasks. Nevertheless, the correct position to apply dropout has rarely been discussed, and different positions have been employed depending on the practitioner…