kamwoh/orthohash
[NeurIPS 2021] Official implementation of the paper "One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective"
This project helps machine learning engineers and researchers simplify the training of deep hashing models for efficient image retrieval. It takes in raw image datasets, trains a model with a single, streamlined objective, and outputs compact binary codes (hashes) for each image. These hashes enable quick searching and matching of similar images, making large-scale image databases more manageable.
Use this if you need to perform fast and accurate image retrieval from large datasets by converting high-dimensional image data into compact binary codes.
Not ideal if your primary goal is general image classification or object detection, as this is specialized for deep hashing and retrieval.
Stars
98
Forks
8
Language
Python
License
BSD-3-Clause
Category
Last pushed
Feb 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kamwoh/orthohash"
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)