[v2] Introduce AbsTaskAnyClustering #2880
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
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
There was a problem hiding this comment.
Pull Request Overview
This PR replaces the legacy clustering task abstractions with the new unified AbsTaskAnyClustering, updates all clustering tasks (text and image) to inherit from it, refactors the evaluator to handle both modalities, and removes the old image‐only clustering evaluator and base classes.
- Introduce
AbsTaskAnyClusteringand deprecateAbsTaskClustering/AbsTaskImageClustering - Update all clustering task classes to extend
AbsTaskAnyClustering, addinginput_column_name/label_column_nameas needed - Refactor
ClusteringEvaluatorto support image/text modalities and remove specializedImageClusteringEvaluator
Reviewed Changes
Copilot reviewed 55 out of 55 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
mteb/abstasks/AbsTaskAnyClustering.py |
New unified clustering base; duplicate label counting logic needs review |
mteb/tasks/Image/ImageClustering/eng/CIFAR.py |
Missing input_column_name override for CIFAR tasks |
mteb/tasks/Image/ImageClustering/eng/TinyImageNet.py |
Correctly adds input_column_name/label_column_name overrides |
mteb/evaluation/evaluators/ClusteringEvaluator.py |
Updated to support image/text, import paths correct |
mteb/abstasks/__init__.py |
Imports updated to include new clustering base |
Multiple mteb/tasks/Clustering/... files |
Updated to inherit from AbsTaskAnyClustering |
Removal of AbsTaskClustering.py and AbsTaskImageClustering.py |
Old bases and image evaluator removed |
Samoed
approved these changes
Jul 6, 2025
|
Yep! On it. |
|
Looked at v_measures for some image and text tasks from v1. Note that ClusteringFast was not implemented in MIEB so that's not been touched in this PR.
|
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.
Fixes #2434
If you add a model or a dataset, please add the corresponding checklist: