enter-i-username/MSNet
[TGRS 2024] MSNet: Self-Supervised Multiscale Network with Enhanced Separation Training for Hyperspectral Anomaly Detection.
This project helps remote sensing professionals find unusual or unexpected objects and materials in satellite or aerial hyperspectral images. It takes raw hyperspectral image data as input and produces a 'detection map' highlighting areas that deviate significantly from the background. Environmental scientists, geological surveyors, and defense analysts who need to identify anomalies without prior examples would find this useful.
No commits in the last 6 months.
Use this if you need to automatically identify rare or unexpected features in hyperspectral imagery, especially when you lack labeled data or specific examples of what constitutes an 'anomaly'.
Not ideal if you have extensive labeled datasets of known anomalies or if your primary goal is general object classification rather than outlier detection.
Stars
19
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jul 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/enter-i-username/MSNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.