whieya/Learning-to-compose
[ICLR'24] Learning to Compose: Improving Object Centric Learning by Injecting Compositionality
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.
Stars
8
Forks
1
Language
Python
License
—
Category
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.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)