thaiminhpv/RelaHash
Official implementation of IEEE Access 2023 paper: "RelaHash: Deep Hashing with Relative Position"
RelaHash helps machine learning engineers and researchers encode high-dimensional data, like images, into compact binary codes. This process, called deep hashing, makes it faster and more efficient to find similar items in large datasets. It takes a dataset of images and outputs a model capable of generating these compressed codes for new images, improving the speed and accuracy of similarity searches.
No commits in the last 6 months.
Use this if you need to perform very fast nearest neighbor searches or similarity matching on large collections of high-dimensional data, especially images, by converting them into efficient binary representations.
Not ideal if your primary goal is not efficient similarity search or if you are working with non-image data where other deep learning techniques are more established.
Stars
50
Forks
5
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thaiminhpv/RelaHash"
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)