search

wusize / CLIPSelf

[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
https://arxiv.org/abs/2310.01403
Other
149 stars 8 forks source link

the Mean Accuracy in table1 means evaluation of ovcoco(65) or coco(80)? #1

Open eternaldolphin opened 9 months ago

wusize commented 9 months ago

coco(80)

eternaldolphin commented 8 months ago

do you have the macc of lvis?