youngkyunJang/SPQ
Self-supervised Product Quantization for Deep Unsupervised Image Retrieval - ICCV2021
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.
Stars
87
Forks
10
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)