[QUESTION] [Multi-label classification] Does an unbalanced class distribution cause problems during training?

Open

#964 opened on Sep 2, 2026 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question

Dominant language: Python
Stars: 1.7k
Forks: 116
Avg merge: 2d 21h
Merged PRs (30d): 6

Description

I want to train a multi-class image classification model using LightlyTrain. My dataset will contain only the following 11 class/label combinations.

### Data Distribution

| Class/label combination | Number of images |
|---|---:|
| Class3 | 1,756 |
| Class2 | 1,441 |
| Class9 | 1,169 |
| Class4 | 327 |
| Class5+Class8 | 215 |
| Class1+Class9 | 213 |
| Class2+Class5 | 206 |
| Class1 | 202 |
| Class3+Class7 | 182 |
| Class5 | 173 |
| Class5+Class9 | 111 |

The total number of images is 5,995.

The group with the highest number of samples contains 1,756 images, while the group with the lowest number of samples contains 111 images.

### My Question

Does this level of data imbalance pose a significant problem during multi-class classification training with LightlyTrain?

Do you have any recommendations for this situation?

Thank you.

Contributor guide

Open the contributing guide

First steps

Read the whole issue, then the project's contributing guide.
Comment on the issue to say you are picking it up — it saves two people doing the same work.
Fork the repository and make your change on a branch.
Open a pull request that references the issue number.

Research direction

No file, test, or entry point is identified; start by reviewing the reported 11-label distribution and the LightlyTrain training guidance relevant to multi-class image classification. Done means providing a project-specific answer on whether this imbalance is problematic and documenting applicable recommendations.

Written by the indexing model from the issue text.

Assessment

Tech stack: python
Domain: computer-vision, machine-learning
Issue type: Documentation
Difficulty: 5/5
Estimated time: Over a week
Activity status: Active
Clarity: Needs clarification
Newbie friendliness: 30/100