Wavelet Packet Power Spectrum Kullback-Leibler Divergence: A New Metric for Image Synthesis

no code implementations • 23 Dec 2023 • Lokesh Veeramacheneni, Moritz Wolter, Juergen Gall

In response, we propose a new frequency band-based quality metric, which opens a door into the frequency domain yet, at the same time, preserves spatial aspects of the data.

Image Generation

Towards generalizing deep-audio fake detection networks

1 code implementation • 22 May 2023 • Konstantin Gasenzer, Moritz Wolter

Today's generative neural networks allow the creation of high-quality synthetic speech at scale.

Face Swapping

Canonical convolutional neural networks

1 code implementation • 3 Jun 2022 • Lokesh Veeramacheneni, Moritz Wolter, Reinhard Klein, Jochen Garcke

We introduce canonical weight normalization for convolutional neural networks.

Model Compression Tensor Decomposition

Feature Selection on Quantum Computers

1 code implementation • 24 Mar 2022 • Sascha Mücke, Raoul Heese, Sabine Müller, Moritz Wolter, Nico Piatkowski

In machine learning, fewer features reduce model complexity.

feature selection

On the effects of biased quantum random numbers on the initialization of artificial neural networks

1 code implementation • 30 Aug 2021 • Raoul Heese, Moritz Wolter, Sascha Mücke, Lukas Franken, Nico Piatkowski

Recent advances in practical quantum computing have led to a variety of cloud-based quantum computing platforms that allow researchers to evaluate their algorithms on noisy intermediate-scale quantum (NISQ) devices.

Wavelet-Packets for Deepfake Image Analysis and Detection

2 code implementations • 17 Jun 2021 • Moritz Wolter, Felix Blanke, Raoul Heese, Jochen Garcke

Additionally, this paper proposes to learn a model for the detection of synthetic images based on the wavelet-packet representation of natural and GAN-generated images.

Face Swapping

Quantum Circuit Evolution on NISQ Devices

no code implementations • 23 Dec 2020 • Lukas Franken, Bogdan Georgiev, Sascha Mücke, Moritz Wolter, Raoul Heese, Christian Bauckhage, Nico Piatkowski

The results provide intuition on how randomized search heuristics behave on actual quantum hardware and lay out a path for further refinement of evolutionary quantum gate circuits.

Neural network compression via learnable wavelet transforms

1 code implementation • 20 Apr 2020 • Moritz Wolter, Shaohui Lin, Angela Yao

Linear layers still occupy a significant portion of the parameters in recurrent neural networks (RNNs).

Data Compression Neural Network Compression

Object-centered Fourier Motion Estimation and Segment-Transformation Prediction

1 code implementation • 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 2020 • Moritz Wolter, Angela Yao, and Sven Behnke

The ability to anticipate the future is essential for ac-tion planning in autonomous systems.

Motion Estimation Object +1

Unsupervised and Generic Short-Term Anticipation of Human Body Motions

no code implementations • 13 Dec 2019 • Kristina Enes, Hassan Errami, Moritz Wolter, Tim Krake, Bernhard Eberhardt, Andreas Weber, Jörg Zimmermann

Exploring the influence of the number of delays on the reconstruction and prediction of various motion classes, we show that the anticipation errors in our results are comparable or even better for very short anticipation times ($<0. 4$ sec) to a recurrent neural network based method.

Sequence Prediction using Spectral RNNs

2 code implementations • 13 Dec 2018 • Moritz Wolter, Juergen Gall, Angela Yao

Fourier methods have a long and proven track record as an excellent tool in data processing.

Time Series Time Series Analysis

Complex Gated Recurrent Neural Networks

1 code implementation • NeurIPS 2018 • Moritz Wolter, Angela Yao

Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures.

Human motion prediction motion prediction +3