Applying different Channel Attention Modules (CAMs) on Transformer-based model for 3D hypercloud segmentation in a geological application. Find our paper here.
Download Tinto data from RODARE.
First prepare KNN points:
python find_kNN_for_training.py
python find_kNN_for_testing.py
Then train and test all models:
Train_and_Test_CAM-Transformer.sh
Visualize Channel Attention:
python Visualize_CAM.py
Cite the paper here:
Rizaldy, A., Ghamisi, P., and Gloaguen, R.: Channel Attention Module for Segmentation of 3D Hyperspectral Point Clouds in Geological Applications, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-4/W11-2024, 103–109, https://doi.org/10.5194/isprs-archives-XLVIII-4-W11-2024-103-2024, 2024.