Implementation of Consistency-based anomaly detection (ConAD) from paper 'Anomaly Detection With Multiple-Hypotheses Predictions' with MNIST dataset [TensorFlow Version].
Simplified ConAD architecture.
Graph of ConAD.
Restoration result by CondAD.
Box plot and histogram of restoration loss in test procedure.
Latent space of each class.
- Python 3.7.4
- PyTorch 1.1.0
- Numpy 1.17.1
- Matplotlib 3.1.1
- Scikit Learn (sklearn) 0.21.3
[1] Duc Tam Nguyen, et al. (2018 arXiv, 2019 ICML). Anomaly Detection With Multiple-Hypotheses Predictions. ICML 2019.