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

Performance of YOSO #12

Open

canglangzhige opened this issue Jul 10, 2023 · 0 comments

canglangzhige commented Jul 10, 2023

Thanks for your work!

The paper points that YOLO delivers competitive performance compared to state-of-the-art models.

In fact, currently, much better results may be achieved both for COCO and Cityscapes datasets. For COCO dataset the PQ = 59.5 is obtained by OpenSeeD (see: https://paperswithcode.com/sota/panoptic-segmentation-on-coco-minival) and PQ of about 70 may be achieved for the Cityscapes dataset (https://paperswithcode.com/sota/panoptic-segmentation-on-cityscapes-val).

The presented approach reaches only 46.4 and 52.5, respectively, far from the state-of-the-art solutions.

It seems that YOSO has sacrificed precision heavily in pursuit of real-time performance？

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