1) Do Vision Transformers See Like Convolutional Neural Networks? (2021)

2) Masked autoencoders are scalable vision learners (2022)

발표자 - 김지은

발표자료 링크 - https://1drv.ms/b/s!AtiR1XA-D_8VgZMhof0Byi4CQuM-6w?e=L4erXV