K set of InfoNCE Loss at Region-Level Contrastive Alignment

IDEA-Research / T-Rex

API for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

https://deepdataspace.com/home

Other

1.98k stars 120 forks source link

K set of InfoNCE Loss at Region-Level Contrastive Alignment #50

Closed urbaneman closed 2 months ago

urbaneman commented 2 months ago

What do you set K in L_algin?

Visual Prompts only choose once of every different categories? Is this correct?

Mountchicken commented 2 months ago

Hi @urbaneman K is the number of categories in each image. Given an image with three categories A, B, and C, then we will extract three visual prompt embeddings for each category.

urbaneman commented 2 months ago

I got. As I understand it. This paper seems to have a very large workload. THANKS for your great work.