Home

Awesome

LREN

We provide a Tensorflow implementation of LREN: Low-Rank Embedded Network for Sample-Free Hyperspectral Anomaly Detection (AAAI2021).

Framework of LREN:

Schematic Diagram

Prerequisites

Citation

If you use this code for your research, please cite:

Jiang, K., Xie, W., Lei, J., Jiang, T., & Li, Y. (2021). LREN: Low-Rank Embedded Network for Sample-Free Hyperspectral Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4139-4146.

Running Code

In this code, you can run our models on on four benchmark hyperspectral datasets, including SanDiego, Hydice, Coast, and Pavia.

Usage

python run_main_LREN.py

Result

Hyperspectral Datasets

For the ease of reproducibility. We provide experimental results on hyperspectral datasets as belows:

DatasetAUC(P_d, P_f)AUC(P_f, \tau)
SanDiego0.98970.0134
Hydice0.99980.0102
Coast0.99820.0276
Pavia0.99250.0433
Average0.99510.0236

Detection_Results

Extension

Since our approach is based on the following three properties:

  1. The background (i.e., the normal instances) still preserves a low-rank property lying in a low-dimensional manifold.
  2. The presence probability of the anomaly is much lower than that of the background (i.e., the normal instances).
  3. The latent representation serves the anomaly estimation, which optimally updates the parameters of the deep latent space.

LREN is applicable to anomaly detection tasks that satisfy these three properties. We conducted experiments on Outlier Detection DataSets (ODDS) to demonstrate the effectiveness of LREN in other anomaly detection tasks.

DatasetAUC(P_d, P_f)AUC(P_f, \tau)PrecisionRecallF1
Thyroid0.99100.09800.85710.64520.7362
Arrhythmia0.83530.04900.63890.4510.5287