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.
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
Some questions regarding the paper #70
Comments
Hi,
Regards, |
@eg4000 Thanks, I got everything. Here we can clearly see that the soft score is way higher than the hard score. Also, any chance you can please publish your recent achieved scores? |
We managed to get better scaled soft scores in past experiments. See #60, #8. The latest mAP was ~52%. You can compute it here. The CRF is a separate paper. Regards, |
Thanks |
I really enjoyed reading the paper, and the results look really promising.
Would love to ask several small details I did not understand though:
You wrote in the paper:
Ok, I understand it would punish smaller IoU detections, thus making detections more tight, and sensitive to occlusions like you said.
However, we have the smooth L1 loss from the regression which should penalize the network for having tight boxes already, so how does this log loss mixing IoU and predicted c_iou score achieving your target?
In the ablation experiments, the basic RetinaNet outperformed the Base+NMS version, which to my understanding is effectively the same, and it's mentioned that it might be due to better implementations in the RetinaNet you tested with.
The gap there is huge, did you try implement your architecture on top of THAT specific RetinaNet framework? I'd expect then the Base+NMS version to be equal and perhaps the final results would significally raise as well.
May I know which RetinaNet implementation you used in the ablation tests? I guess it wasn't the base Keras implementation which this architecture is built on...
Lastly, isn't it weird that Faster R-CNN got such a low score?
Did you try adjusting it's anchors to smaller object sizes?
Thanks!
The text was updated successfully, but these errors were encountered: