salesforce / ALBEF

Code for ALBEF: a new vision-language pre-training method
BSD 3-Clause "New" or "Revised" License
1.46k stars 193 forks source link

segmentation layer #68

Open chaochen99 opened 2 years ago

chaochen99 commented 2 years ago

Hi,

Why use the sixth layer as the segmentation, has the author tried to use other layers as the segmentation? such as 8,4?

Thanks!

LiJunnan1992 commented 2 years ago

Hi, we have reported the results using other layers in the paper's appendix, thanks.