Tweeted By @ak92501
Vision Transformer with Progressive Sampling
— AK (@ak92501) August 5, 2021
pdf: https://t.co/UW4Q8YmWPi
abs: https://t.co/usaqUHuSkS
When trained from scratch on ImageNet, PS-ViT performs 3.8% higher than the vanilla ViT in terms of top-1 accuracy with about 4× fewer parameters and 10× fewer FLOPs pic.twitter.com/ikxFIUuk9M