FIX union calculation in hungarian_miou #7
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Member
|
Thanks a lot for the fix! Yes, I agree the bug isn't likely to change the order of the benchmarked methods. I'll try to update the manuscript after re-running the evaluation. |
Member
|
Hi, the new SlotFormer result is updated in PR#8 now. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hey there, we found a small bug in the calculation of the union in the hungarian_miou method.
Your code uses addition instead of sum and logical_or which results in an upper bound of 0.5 for perfect predictions. For instance, if true_oh == pred_oh, the intersections are simply the sizes of the instances and so should the unions be as well. With the addition however, you count the instance sizes twice which results in the upper bound of 0.5 in this case. An easy fix is to subtract the intersection from this calculation.
Importantly, this bug is most likely only a scaling issue and should not change published results beyond this point.
Best, Johannes