loeweX/ComplexAutoEncoder
Code for the paper: Complex-Valued Autoencoders for Object Discovery
This project offers a method for identifying distinct objects within complex images. It takes an image containing multiple overlaid or grouped shapes and figures as input, and outputs a representation that separates individual objects. This is primarily useful for researchers and machine learning practitioners exploring advanced object recognition and scene understanding.
No commits in the last 6 months.
Use this if you are a researcher or ML engineer interested in novel approaches to disentangling object features from their spatial relationships within an image.
Not ideal if you are looking for an out-of-the-box solution for standard object detection tasks in real-world applications.
Stars
59
Forks
7
Language
Python
License
MIT
Last pushed
Feb 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/loeweX/ComplexAutoEncoder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Naresh1318/Adversarial_Autoencoder
A wizard's guide to Adversarial Autoencoders
mseitzer/pytorch-fid
Compute FID scores with PyTorch.
acids-ircam/RAVE
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
ratschlab/aestetik
AESTETIK: Convolutional autoencoder for learning spot representations from spatial...
jaanli/variational-autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)