DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows

1 code implementation • 30 May 2021 • Samuel von Baußnern, Johannes Otterbach, Adrian Loy, Mathieu Salzmann, Thomas Wollmann

We demonstrate the effectiveness of our approach using an ESPNet trained on the Cityscapes dataset as segmentation model, an affine Normalizing Flow as density estimator and use blue noise to ensure homogeneous sampling.

Image Segmentation Segmentation +1

Training Competitive Binary Neural Networks from Scratch

1 code implementation • 5 Dec 2018 • Joseph Bethge, Marvin Bornstein, Adrian Loy, Haojin Yang, Christoph Meinel

In our work, we focus on increasing the performance of binary neural networks without such prior knowledge and a much simpler training strategy.