leftthomas/NPID

A PyTorch implementation of NPID based on CVPR 2018 paper "Unsupervised Feature Learning via Non-Parametric Instance Discrimination"

19
/ 100
Experimental

This project helps machine learning engineers and researchers learn meaningful representations from image datasets without requiring human-labeled categories. By training on images, it outputs feature embeddings that capture visual similarities, enabling tasks like image search or anomaly detection. It's designed for those working with large, unlabeled image collections who need to extract visual patterns.

No commits in the last 6 months.

Use this if you need to extract useful visual features from image data without the time or resources to manually label every image.

Not ideal if you already have perfectly labeled datasets or if your task relies on very specific, human-defined categories.

unsupervised-learning image-feature-extraction computer-vision-research representation-learning data-mining
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

Python

License

Last pushed

Feb 10, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/leftthomas/NPID"

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