Added symbol for Dense Faster R-CNN model#143
Open
shoaibahmed wants to merge 1 commit intomsracver:masterfrom
shoaibahmed:master
Open
Added symbol for Dense Faster R-CNN model#143shoaibahmed wants to merge 1 commit intomsracver:masterfrom shoaibahmed:master
shoaibahmed wants to merge 1 commit intomsracver:masterfrom
shoaibahmed:master
Conversation
|
It's just like the skip connection of FCN but your implementation is pooling down. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Added a new model for Faster R-CNN which I call as dense as the model contains skip connections from each of the blocks from ResNet for feeding into the final classification head.
The availability of low-level features along with the more abstract features might result in an improvement in the overall classification performance of the system.
This approach has been tested for two of the tasks that I have been working on and has produced better results as compared to the original ResNet-101 model.