whieya/Learning-to-compose

[ICLR'24] Learning to Compose: Improving Object Centric Learning by Injecting Compositionality

34
/ 100
Emerging

This project offers a method for improving how AI models understand and represent complex scenes by focusing on individual objects and their relationships. It takes in visual datasets, such as ClevrTex, MSN, or PTR, and outputs trained models that are better at disentangling and composing objects within images. This is primarily useful for AI researchers and machine learning engineers developing next-generation computer vision and scene understanding systems.

Use this if you are a researcher or engineer working on object-centric learning and want to enhance your models' ability to recognize and combine distinct objects within visual data.

Not ideal if you are looking for a pre-trained model for immediate application in tasks like image classification or object detection without further research and development.

computer-vision-research scene-understanding object-centric-AI machine-learning-research AI-model-development
No Package No Dependents
Maintenance 6 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

Last pushed

Nov 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/whieya/Learning-to-compose"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.