ZhiyuanDang/NNM

The PyTorch official implementation of the CVPR2021 Poster Paper NNM: Nearest Neighbor Matching for Deep Clustering.

35
/ 100
Emerging

This project helps machine learning researchers or practitioners in computer vision to automatically group similar images together without needing pre-labeled data. It takes a collection of images as input and organizes them into meaningful clusters based on their visual features, identifying underlying categories. The output is a set of clustered images and can include visualizations of representative images for each group.

No commits in the last 6 months.

Use this if you need to discover natural groupings within an unlabeled image dataset, such as categorizing product images, scientific samples, or surveillance footage, to gain insights or prepare for further analysis.

Not ideal if you already have labeled data and need to perform supervised classification, or if your primary goal is object detection or image generation.

image-clustering unsupervised-learning computer-vision data-exploration image-categorization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

57

Forks

6

Language

Python

License

Last pushed

Dec 15, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ZhiyuanDang/NNM"

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