562 citations · 1.4k across the 12 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CV2021★ 353 cited
Early Convolutions Help Transformers See Better
Tete Xiao, Mannat Singh, Eric Mintun +3
Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and tra…
cs.CV2021★ 10 cited
On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness
Eric Mintun, Alexander Kirillov, Saining Xie
Invariance to a broad array of image corruptions, such as warping, noise, or color shifts, is an important aspect of building robust models in computer vision. Recently, several ne…