fcakir/deep-mihash
Code for papers "Hashing with Mutual Information" (TPAMI 2019) and "Hashing with Binary Matrix Pursuit" (ECCV 2018)
This is a research code for developers and researchers working with image datasets and deep learning models. It provides a MATLAB implementation for advanced hashing techniques that improve how efficiently and accurately similar images are retrieved from large collections. You input large image datasets and deep learning models, and it outputs hashed representations of those images along with performance metrics like mean Average Precision (mAP).
No commits in the last 6 months.
Use this if you are a researcher or developer exploring advanced deep hashing methods, especially those involving mutual information or binary matrix pursuit, to improve image retrieval performance.
Not ideal if you are looking for an out-of-the-box application for general image search, or if you prefer working outside of the MATLAB environment with pre-built models.
Stars
19
Forks
6
Language
MATLAB
License
—
Category
Last pushed
Oct 11, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/fcakir/deep-mihash"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cosmosgl/graph
GPU-accelerated force graph layout and rendering
Clay-foundation/model
The Clay Foundation Model - An open source AI model and interface for Earth
nomic-ai/nomic
Nomic Developer API SDK
omoindrot/tensorflow-triplet-loss
Implementation of triplet loss in TensorFlow
sashakolpakov/dire-jax
DImensionality REduction in JAX