ZY-LIi/IEEE_TGRS_DEMAE

Pre-train a Masked Autoencoder with the idea of Diffusion Models for Hyperspectral Image Classification.

13
/ 100
Experimental

This project helps remote sensing analysts classify objects and materials in hyperspectral images more accurately, even when they have very few labeled examples for training. It takes raw hyperspectral image data and, after a pre-training step, outputs a classification of the image's contents. This is useful for scientists or engineers working with satellite imagery, environmental monitoring, or geological surveys.

No commits in the last 6 months.

Use this if you need to classify objects within hyperspectral images and are challenged by a limited number of labeled training samples.

Not ideal if you are working with standard RGB images or already have abundant labeled data for your hyperspectral classification task.

remote-sensing hyperspectral-imaging environmental-monitoring geospatial-analysis material-identification
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

Last pushed

Sep 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ZY-LIi/IEEE_TGRS_DEMAE"

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