22k citations · 22.5k across the 18 of their papers we have counts for
3 papers · 1 filter
FlexiViT: One Model for All Patch Sizes
Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov +7
Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher a…
Decoder Denoising Pretraining for Semantic Segmentation
Emmanuel Brempong Asiedu, Simon Kornblith, Ting Chen +3
Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the…
Simple Open-Vocabulary Object Detection with Vision Transformers
Matthias Minderer, Alexey Gritsenko, Austin Stone +11
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are…