[Feature]: add semantic FPN for panoptic segmentation #4969
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Outdated suggestions cannot be applied.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.
This PR continues on PR #953.
It refactors the semantic head and adds semantic FPN for panoptic segmentation. The semantic FPN is used as a decoder in the semantic segmentation head. The
FusedSemanticHead
for HTC is refactored and inherits from the newSemanticHead
. Thus, it can also be used for panoptic segmentation while providing semantic features in HTC and SCNet.The BC-breaking of names of convolutional layers in the semantic head is handled by
_load_from_state_dict
. Therefore, the old models can still be successfully loaded for inference and the new models will have different key names in the semantic heads.