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

[15] ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases #15

Open

omocomo opened this issue Dec 26, 2022 · 0 comments

Assignees

Labels

Contributor

omocomo commented Dec 26, 2022

Links

Paper : https://arxiv.org/abs/2103.10697
Github : https://github.com/facebookresearch/convit

한 줄 요약

Facebook AI에서 작성한 논문으로, Vision Transformer에 soft한 inductive bias를 더해줄 수 있는 방법을 제안한다.

선택 이유

What do Vision Transformers Learn? A Visual Exploration 이 논문을 읽으려다 ConViT를 알게 됐는데, CNN과 ViT가 어떻게 결합될 수 있는지 궁금해서 읽어보았다.

omocomo added the Transformer label

omocomo self-assigned this

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