output
20022026
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing 2020Show all

20 papers · 1 filter

cond-mat.stat-mech2020★ 7 cited

Generative Neural Samplers for the Quantum Heisenberg Chain

Johanna Vielhaben, Nils Strodthoff

Generative neural samplers offer a complementary approach to Monte Carlo methods for problems in statistical physics and quantum field theory. This work tests the ability of genera…

cs.NI2020★ 44 cited

6G in the Sky: On-Demand Intelligence at the Edge of 3D Networks

Emilio Calvanese Strinati, Sergio Barbarossa, Taesang Choi +10

6G will exploit satellite, aerial and terrestrial platforms jointly to improve radio access capability and to unlock the support of on-demand edge cloud services in the three dimen…

cs.CV2020★ 14 cited

Going beyond Free Viewpoint: Creating Animatable Volumetric Video of Human Performances

Anna Hilsmann, Philipp Fechteler, Wieland Morgenstern +4

In this paper, we present an end-to-end pipeline for the creation of high-quality animatable volumetric video content of human performances. Going beyond the application of free-vi…

cs.LG2020★ 897 cited

A Unifying Review of Deep and Shallow Anomaly Detection

Lukas Ruff, Jacob R. Kauffmann, Robert A. Vandermeulen +5

Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text.…

eess.SP2020

Feedback Prediction for Proactive HARQ in the Context of Industrial Internet of Things

Baris Göktepe, Tatiana Rykova, Thomas Fehrenbach +2

In this work, we investigate proactive Hybrid Automatic Repeat reQuest (HARQ) using link-level simulations for multiple packet sizes, modulation orders, BLock Error Rate (BLER) tar…

cs.MM2020★ 36 cited

Kalman Filter-based Head Motion Prediction for Cloud-based Mixed Reality

Serhan Gül, Sebastian Bosse, Dimitri Podborski +2

Volumetric video allows viewers to experience highly-realistic 3D content with six degrees of freedom in mixed reality (MR) environments. Rendering complex volumetric videos can re…

cs.CV2020★ 19 cited

Explanation-Guided Training for Cross-Domain Few-Shot Classification

Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek +3

Cross-domain few-shot classification task (CD-FSC) combines few-shot classification with the requirement to generalize across domains represented by datasets. This setup faces chal…

cs.IT2020★ 22 cited

Over-The-Air Computation in Correlated Channels

Matthias Frey, Igor Bjelakovic, Slawomir Stanczak

Over-the-Air (OTA) computation is the problem of computing functions of distributed data without transmitting the entirety of the data to a central point. By avoiding such costly t…

eess.SP2020

Channel covariance estimation in multiuser massive MIMO systems with an approach based on infinite dimensional Hilbert spaces

Renato Luis Garrido Cavalcante, Slawomir Stanczak

We propose a novel algorithm to estimate the channel covariance matrix of a desired user in multiuser massive MIMO systems. The algorithm uses only knowledge of the array response…

cs.LG2020★ 3 cited

Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)

Arturo Marban, Daniel Becking, Simon Wiedemann +1

Deep neural networks (DNN) have shown remarkable success in a variety of machine learning applications. The capacity of these models (i.e., number of parameters), endows them with…

eess.SP2020

Hybrid data and model driven algorithms for angular power spectrum estimation

Renato Luis Garrido Cavalcante, Slawomir Stanczak

We propose two algorithms that use both models and datasets to estimate angular power spectra from channel covariance matrices in massive MIMO systems. The first algorithm is an it…

cs.CV2020★ 14 cited

Style Your Face Morph and Improve Your Face Morphing Attack Detector

Clemens Seibold, Anna Hilsmann, Peter Eisert

A morphed face image is a synthetically created image that looks so similar to the faces of two subjects that both can use it for verification against a biometric verification syst…

cs.LG2020★ 1 cited

Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training

Simon Wiedemann, Temesgen Mehari, Kevin Kepp +1

Deep Neural Networks are successful but highly computationally expensive learning systems. One of the main sources of time and energy drains is the well known backpropagation (back…

cs.CV2020★ 31 cited

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Gary S. W. Goh, Sebastian Lapuschkin, Leander Weber +2

Integrated Gradients as an attribution method for deep neural network models offers simple implementability. However, it suffers from noisiness of explanations which affects the ea…

astro-ph.IM2020★ 23 cited

Thermophysical modelling and parameter estimation of small solar system bodies via data assimilation

M. Hamm, I. Pelivan, M. Grott +1

Deriving thermophysical properties such as thermal inertia from thermal infrared observations provides useful insights into the structure of the surface material on planetary bodie…

cs.LG2020★ 1.5k cited

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Wojciech Samek, Grégoire Montavon, Sebastian Lapuschkin +2

With the broader and highly successful usage of machine learning in industry and the sciences, there has been a growing demand for Explainable AI. Interpretability and explanation…

cs.CV2020★ 171 cited

Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI

Leila Arras, Ahmed Osman, Wojciech Samek

The rise of deep learning in today's applications entailed an increasing need in explaining the model's decisions beyond prediction performances in order to foster trust and accoun…

cs.MM2020★ 41 cited

Cloud Rendering-based Volumetric Video Streaming System for Mixed Reality Services

Serhan Gül, Dimitri Podborski, Jangwoo Son +4

Volumetric video is an emerging technology for immersive representation of 3D spaces that captures objects from all directions using multiple cameras and creates a dynamic 3D model…

hep-lat2020★ 45 cited

Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning

Stefan Bluecher, Lukas Kades, Jan M. Pawlowski +2

Machine learning has the potential to aid our understanding of phase structures in lattice quantum field theories through the statistical analysis of Monte Carlo samples. Available…

cs.MM2020★ 61 cited

Low-latency Cloud-based Volumetric Video Streaming Using Head Motion Prediction

Serhan Gül, Dimitri Podborski, Thomas Buchholz +2

Volumetric video is an emerging key technology for immersive representation of 3D spaces and objects. Rendering volumetric video requires lots of computational power which is chall…