Skip to content
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

[Reimplementation] Not able to reimplement the final performance #6

Open
3 tasks done
Sino0904 opened this issue May 7, 2024 · 0 comments
Open
3 tasks done

Comments

@Sino0904
Copy link

Sino0904 commented May 7, 2024

Prerequisite

💬 Describe the reimplementation questions

I tried to re-implement the GOOD results for voc-to-nonvoc setting and I am getting a lower performance. I trainied bot the stages from scratch following the instructions (i.e. generated depth and normal images, trained stage1 and stage 2). Here are the final results:

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.041
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.064
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.040
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.026
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.051
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.073
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.173
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.243
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 30 ] = 0.284
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 50 ] = 0.336
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.388
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.448
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=500 ] = 0.469
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.220
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.472
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.611

As you can see, the AR@100 is 0.5% lower than what is reported in the paper. On comparing pseudoboxes that I get from stage 1 to the provided pseudoboxes, there are some differences. Is there a way to replicate stage-1 output?

Thanks!

Environment

Followed the same environment as given in the instructions.

Expected results

No response

Additional information

No response

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant