BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks

no code implementations • 14 Mar 2021 • Manoj Rohit Vemparala, Alexander Frickenstein, Nael Fasfous, Lukas Frickenstein, Qi Zhao, Sabine Kuhn, Daniel Ehrhardt, Yuankai Wu, Christian Unger, Naveen Shankar Nagaraja, Walter Stechele

The distilled models exhibit their strength against all white box attacks with an exception of C&W.

BinaryCoP: Binary Neural Network-based COVID-19 Face-Mask Wear and Positioning Predictor on Edge Devices

1 code implementation • 6 Feb 2021 • Nael Fasfous, Manoj-Rohit Vemparala, Alexander Frickenstein, Lukas Frickenstein, Walter Stechele

Convolutional neural networks (CNNs) offer an excellent solution for face recognition and classification of correct mask wearing and positioning.

Face Recognition General Classification

L2PF -- Learning to Prune Faster

no code implementations • 7 Jan 2021 • Manoj-Rohit Vemparala, Nael Fasfous, Alexander Frickenstein, Mhd Ali Moraly, Aquib Jamal, Lukas Frickenstein, Christian Unger, Naveen-Shankar Nagaraja, Walter Stechele

In this context, we present Learning to Prune Faster which details a multi-task, try-and-learn method, discretely learning redundant filters of the CNN and a continuous action of how long the layers have to be fine-tuned.

Autonomous Driving

ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks

no code implementations • 27 Jul 2020 • Alexander Frickenstein, Manoj-Rohit Vemparala, Nael Fasfous, Laura Hauenschild, Naveen-Shankar Nagaraja, Christian Unger, Walter Stechele

Model compression techniques, such as pruning, are emphasized among other optimization methods for solving this problem.

Model Compression