alldbi/Factorized-Spatial-Embeddings
Tensorflow implementation of Unsupervised learning of object landmarks by factorized spatial embeddings
This project helps researchers and developers working with image analysis to automatically identify key points or 'landmarks' on objects within images, even without needing to manually label them beforehand. You provide a dataset of images, and it outputs a model capable of pinpointing features like eyes or corners of objects across new images. This tool is ideal for computer vision engineers and academic researchers focused on facial recognition, object analysis, or similar fields.
No commits in the last 6 months.
Use this if you need to automatically detect consistent key features on objects in a large image dataset without the time-consuming and expensive process of manual annotation.
Not ideal if you need to detect specific, pre-defined landmarks with high precision where manual labeling is feasible and essential, or if you require real-time inference on edge devices.
Stars
30
Forks
6
Language
Python
License
MIT
Category
Last pushed
Feb 19, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/alldbi/Factorized-Spatial-Embeddings"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cosmosgl/graph
GPU-accelerated force graph layout and rendering
Clay-foundation/model
The Clay Foundation Model - An open source AI model and interface for Earth
nomic-ai/nomic
Nomic Developer API SDK
omoindrot/tensorflow-triplet-loss
Implementation of triplet loss in TensorFlow
sashakolpakov/dire-jax
DImensionality REduction in JAX