youngkyunJang/SPQ

Self-supervised Product Quantization for Deep Unsupervised Image Retrieval - ICCV2021

38
/ 100
Emerging

This project helps build image search systems that can quickly find similar images within very large collections, even without human-labeled data. It takes in a dataset of images and outputs a trained model capable of extracting descriptive features and compact codes for each image. This allows someone managing a large image database to efficiently search and retrieve relevant images.

No commits in the last 6 months.

Use this if you need to set up a fast, scalable image retrieval system for a massive collection of images without the resources to manually label all your data.

Not ideal if you have a small, easily labeled dataset or if your primary goal isn't high-speed, large-scale similarity search.

image-search visual-content-management similarity-matching large-scale-indexing unsupervised-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

87

Forks

10

Language

Python

License

MIT

Last pushed

May 27, 2024

Commits (30d)

0

Get this data via API

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

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