This is the implementation of the following paper:

R. Kaviani Baghbaderani, Y. Qu. H. Qi, C. Stutts, Representative-Discriminative Learning for Open-set Land Cover Classification of Satellite Imagery, European Conference on Computer Vision (ECCV), 2020. [Slides]

• Python 3.6
• TensorFlow 1.15
• Numpy 1.19
• Scipy 1.5.1
• Scikit-learn 0.23.1

The code uses the following datasets:

1. Pavia University (PaviaU)
2. Pavia Center (Pavia)
3. Indian Pines (Indian_pines)

To preprocess the Hyperspcetral data and divide it to Known and Unknown sets:

python preprocessing.py --dataset Indian_pines --unk 3 7

To train the network on known set:

python train_rdosr.py --dataset Indian_pines

1. To test the network on a combination of known and unknown sets:

python test_rdosr.py --dataset Indian_pines

2. Run plot_loss_accu.m which will display the training curves.
3. Run plot_histograms_ROC.m which will display the ROC curve.

Razieh Kaviani Baghbaderani ([email protected])