AlphaCLIP

AlphaCLIP copied to clipboard

Table 6: Performance of Alpha-CLIP in region level captioning

1

Great work! I am confused with Tab .6 result, the performance is Alpha-CLIP with LLaVA-1.5 or fine-tune this model with vicuna-7b on these datasets(RefCOCOg or VG)？

jetyingjia

Do you consider trying Alpha-DINOv2?

1

DINOv2 seems powerful in some applications like CLIP, maybe a similar Alpha-DINOv2 is very useful too

grainseed

Will you provide code for the data generation process?

2

We would like to reproduce your results and are wondering when the data synthesis code will be opened up.

DesertsP

vasatile -> versatile

eltociear