YichuXu/DSFormer
[Neural Networks 2025] Dual Selective Fusion Transformer Network for Hyperspectral Image Classification
This project helps scientists and researchers in remote sensing and earth observation accurately identify different materials or land cover types within an image. It takes raw hyperspectral image data as input and produces a classified map showing what each pixel represents. Remote sensing specialists, environmental scientists, and geologists who work with satellite or aerial imagery for land use mapping, precision agriculture, or environmental monitoring would use this.
Use this if you need to precisely classify regions within high-resolution hyperspectral images, especially in complex environments where distinguishing between similar materials is crucial.
Not ideal if you are working with standard RGB images or require a simple, fast classification for general imagery rather than detailed spectral analysis.
Stars
94
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jan 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YichuXu/DSFormer"
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
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.