Open liuqk3 opened 1 year ago
This could be a problem for the open-vocabulary detection task.
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.
Hi @yuhangzang ,
Thanks for your great work! There is somthing confused me a lot. In the function
forward_test()
ofOVDETR
, 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.