-
Notifications
You must be signed in to change notification settings - Fork 62
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
The experiment reproduction question for 3D semantic segmentation on the 3D-OVS #20
Comments
Hi, Regarding the calculation of mIoU for the "sofa" scene, we calculate the average relevancy scores within the mask region for each relevancy map and select the relevancy map with the highest average response as the final predicted binary map. Regarding the issue with the black segmentation maps you mentioned, could you provide more information? As I'm currently unclear about the specific problem you're encountering. For more details on the implementation aspects of our work, please refer to the supplementary materials of our paper. |
Hi, |
Thank you so much for sharing your great work.
When I used your code and pre-trained weights to reproduce the segmentation results for the "sofa" scene, my mIoU results were calculated to be just over 70. My current calculation method is to calculate mIoU separately for all "three relevancy maps" generated by any "positive" and then average them. I don't know if my calculation manner is correct.
In addition, the segmentation map generated for the 'grey sofa' in the 'sofa' scene is completely black. Do you have any suggestions to help me improve my results?
The text was updated successfully, but these errors were encountered: