search

IDEA-Research / GroundingDINO

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
https://arxiv.org/abs/2303.05499
Apache License 2.0
5.81k stars 613 forks source link

Can GroundingDINO do one-shot detection? #207

Open nickponline opened 11 months ago

nickponline commented 11 months ago

Can Grounding DINO be used for image conditioned one-shot or few-shot detection like this?

image_cond_wiki_circuits_1

The image is from OWL-VIT which can do be prompted with either text or an image patch. I feel that DINO should be able to do the same thing and likely perform better?

AdamMayor2018 commented 11 months ago

Is the problem solved? Same here.

Nancis1130 commented 11 months ago

same problem.

jonomillin commented 10 months ago

Same question!

AdamMayor2018 commented 10 months ago

same here.

nickponline commented 10 months ago

@rentainhe @SlongLiu perhaps you know the answer here and could point us in the right direction?

mikewinn1 commented 10 months ago

same here

Alaric423 commented 5 months ago

Any update here?

YoungSean commented 1 month ago

Please check out NIDS-Net. It includes Grounding-DINO to handle these tasks. It can detect things with just one or a few template images. Moreover, it may not need any training.