yuhangzang / OV-DETR

[Under preparation] Code repo for "Open-Vocabulary DETR with Conditional Matching" (ECCV 2022)
201 stars 18 forks source link

Does OV-DETR really Open-Vocabulary? #8

Open liuqk3 opened 1 year ago

liuqk3 commented 1 year ago

Hi @yuhangzang ,

Thanks for your great work! There is somthing confused me a lot. In the function forward_test() of OVDETR, I found that the clip based text query is still required for detection. However, in real application, do we know the class names of all objects in the test image? If not, how OVDETR detects the unknown objects?

Thanks.

wangchust commented 1 year ago

This could be a problem for the open-vocabulary detection task.

ngthanhtin commented 1 year ago

Hi @liuqk3 , I think it depends on you. You can specify the object names in advance to detect them. Speaking to unknown objects, just set some unknown-related words.