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

[25] data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language #25

Open

Dongwoo-Im opened this issue Mar 21, 2023 · 1 comment

Assignees

Labels

ICML '22 Multi-modality Oral Self-supervised Learning Transformer

Contributor

Dongwoo-Im commented Mar 21, 2023

Links

Paper : https://arxiv.org/abs/2202.03555
Github : https://github.com/facebookresearch/fairseq/tree/main/examples/data2vec

한 줄 요약

Vision, speech, language 도메인에 masked prediction task를 활용한 self-supervised learning objective 제안

선택 이유

Masked prediction objective를 다양한 modality에 어떻게 적용하였는지 궁금해서 선정

Dongwoo-Im added Transformer Self-supervised Learning ICML '22 Multi-modality labels

Dongwoo-Im self-assigned this

Contributor Author

Dongwoo-Im commented Mar 21, 2023

https://dongwoo-im.github.io/papers/review/2023-03-20-data2vec/

Dongwoo-Im added the Oral label

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