Yuhan Zhu comments

Results 2 comments of


                                            Yuhan Zhu

Supervised Contrastive Learning with n_views=1

My understanding is that to make sure that there exist positives in the multiviewed batch, otherwise, the numerator in the loss formula (Eq. 2/3) would be 0.

Request to add new papers: AWT, ProVP, Self-TPT

> I can't open this link: ![image](https://private-user-images.githubusercontent.com/22991938/376034176-876b0b5c-0b1c-4263-ab9d-3725042d8326.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.mWywyAvU_r9jG6xEILD7bV8_UCdPEBYo16i1Z4GoDSo) Hi, this link works for me. Could you please try it again? Thanks!