leftthomas/NPID
A PyTorch implementation of NPID based on CVPR 2018 paper "Unsupervised Feature Learning via Non-Parametric Instance Discrimination"
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.
Stars
14
Forks
1
Language
Python
License
—
Category
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.
Higher-rated alternatives
HROlive/Generative-AI-with-Diffusion-Models
Deep dive on diffusion models, which are a popular choice for text-to-image pipelines,...
harinik05/LeukoDif
Denoising Diffusion Medical Model (DDMM) on PyTorch for generating datasets of Acute...
DavePower-cloud/Diffusion_X-ray_Generator
Diffusion-based generative model for synthesising chest X-ray images using a 3D U-Net-style...
Akshat4112/SpeakerDiff
SpeakerDiff: Denoising Diffusion Probalistic Models on Speaker Embeddings