ovdet
ovdet copied to clipboard
wusize
[CVPR2023] Code Release of Aligning Bag of Regions for Open-Vocabulary Object Detection
Faster-RCNN produces different region proposals on each debug. I found that the file under the path below included a forward function producing different outputs. - mmdetection/mmdet/models/backbones/resnet.py x = self.conv1(x) x...
Thank you for your great work! I want to know how to test trained model on OV-LVIS on other obeject detection datasets like Objects365 and Pascal VOC , can I...
@wusize Hi, I also hope to get your lvis training and test code. The repo link you sent seems to be unavailable, could I trouble you to send the code...
Thanks for great work! BARON uses ResNet50-FPN as backbone when using CLIP as supervision, but uses ResNet50-C4 as backbone when using captions as supervision. I'm curious about why using different...
If it's convenient to provide the code for Grad-CAM++ visualization?
Thank you for your great work! I want to test but I don't find out the model training on OV-LVIS. Can you tell me? I'm looking forward to your reply!
Good day! I would like to commend your paper. Great work on this. I plan on reproducing the results from your paper, particularly the OV-LVIS one. I have successfully run...
Hello author, I'm so sorry to bother you. I try to replicate results on DetPro and BARON using learned prompts but I didn't find relevant code in ovdet, how can...
Hi, Thanks for sharing such a great work exploiting the local scene structure inherently captured by VLMs, a very novel perspective. I have one confusing question after reading the paper....
