Issues
- 0
Cannot reproduce MAP of 1.0
#16 opened by Artcs1 - 0
# of negative samples in the intra scenario
#15 opened by Bhathiya-hw - 4
Grounding DINO
#9 opened by Zesheng666 - 3
- 3
- 2
Inference setup and code for Grounding DINO
#11 opened by Amaia-CARDIEL - 3
OWL-ViT pre-trained models cannot accept some of the longest descriptions
#13 opened by HarukiNishimura-TRI - 1
Implementation of OFA-DOD
#10 opened by xiaofeng94 - 2
the 'is_negative' meaning?
#8 opened by peiliu0408 - 3
I have not find the model proposed in paper "Advancing Referring Expression Segmentation Beyond Single Image"
#6 opened by MI-WENYU - 5
about pre-trained
#3 opened by JunL-Geek - 2
- 2
我跑了下 owl-vit,结果和论文不一致,想请问原因是啥?
#7 opened by hhaAndroid - 4
Some images have no associated annotations?
#5 opened by ImcwjHere - 1
about evaluate
#2 opened by JunL-Geek