New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CBNet - Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) - mAP@50=71.9%, mAP@0.5...0.95=53.3% #4123

Open

AlexeyAB opened this issue Oct 18, 2019 · 0 comments

Labels

want enhancement

Owner

AlexeyAB commented Oct 18, 2019

CBNet looks also like a good backbone.
Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale)

mAP@50 = 71.9%
mAP@0.5...0.95 = 53.3%

In a R-CNN like detector it achieves #1: https://paperswithcode.com/sota/object-detection-on-coco
"CBNet: A Novel Composite Backbone Network Architecture for Object Detection", Sep 2019,
https://arxiv.org/pdf/1909.03625.pdf

AlexeyAB added the want enhancement label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment