New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[10] Do Vision Transformers See Like Convolutional Neural Networks? #10

Open

techzzt opened this issue Aug 16, 2022 · 0 comments

Owner

techzzt commented Aug 16, 2022

Do Vision Transformers See Like Convolutional Neural Networks?

CNN과 ViT의 feature map representation 비교를 통해 ViT 모델이 representation 측면에서 가지는 장점에 대해 작성한 논문
Locality한 특성을 반영하는 cnn 모델과 달리 ViT는 global, local한 정보를 모두 포함하며 각 layer에서 block이 깊어질수록 global한 특성을 보존하고 있음을 확인

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment