Add ID models #234
Merged
Add ID models #234
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
added 2 commits
July 7, 2025 12:56
d7bbe3a to
24871b9
Compare
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #234 +/- ##
==========================================
- Coverage 96.58% 96.40% -0.19%
==========================================
Files 45 47 +2
Lines 5153 5922 +769
==========================================
+ Hits 4977 5709 +732
- Misses 176 213 +37 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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 adds support for appearance-based tracking by introducing ID models for both Bottom-Up and Top-Down architectures.
Bottom-Up ID Model:
This model extends the standard Bottom-Up approach by replacing PAFs with multi-class segmentation maps ("classmaps"). Instead of explicitly grouping keypoints, the model predicts the probability that each keypoint belongs to a specific animal ID. Identity assignment is performed via optimal matching of class probabilities, making explicit grouping unnecessary.
Top-Down ID Model:
In this model, we extend the standard centered-instance pipeline by adding a classification head that predicts animal identity for each centroid-cropped image. Identity classification is computed from the features of the deepest layer of the encoder (the model to learn appearance-based features). The resulting class probabilities are then used to assign instance identities via optimal matching.