output
20022026
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing 2016Show all

9 papers · 1 filter

cs.CL2016★ 271 cited

"What is Relevant in a Text Document?": An Interpretable Machine Learning Approach

Leila Arras, Franziska Horn, Grégoire Montavon +2

Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatic…

cs.CV2016★ 1.1k cited

Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

Sebastian Bosse, Dominique Maniry, Klaus-Robert Müller +2

We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers…

cs.IT2016★ 33 cited

Tracking of Wideband Multipath Components in a Vehicular Communication Scenario

Kim Mahler, Wilhelm Keusgen, Fredrik Tufvesson +2

A detailed understanding of the dynamic processes of vehicular radio channels is crucial for its realistic modeling. In this paper, we present multipath components (MPCs) tracking…

cs.NI2016★ 24 cited

Measurement-Based Wideband Analysis of Dynamic Multipath Propagation in Vehicular Communication Scenarios

Kim Mahler, Wilhelm Keusgen, Fredrik Tufvesson +2

Realistic propagation modeling requires a detailed understanding and characterization of the radio channel properties. This paper is based on channel sounder measurements with 1 GH…

cs.CV2016★ 324 cited

A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment

Rafael Reisenhofer, Sebastian Bosse, Gitta Kutyniok +1

In most practical situations, the compression or transmission of images and videos creates distortions that will eventually be perceived by a human observer. Vice versa, image and…

cs.CV2016

Object Boundary Detection and Classification with Image-level Labels

Jing Yu Koh, Wojciech Samek, Klaus-Robert Müller +1

Semantic boundary and edge detection aims at simultaneously detecting object edge pixels in images and assigning class labels to them. Systematic training of predictors for this ta…

math.OC2016★ 22 cited

A multilevel based reweighting algorithm with joint regularizers for sparse recovery

Jackie Ma, Maximilian März

Sparsity is one of the key concepts that allows the recovery of signals that are subsampled at a rate significantly lower than required by the Nyquist-Shannon sampling theorem. Our…

cs.NI2016★ 433 cited

Designing and Implementing Future Aerial Communication Networks

Sathyanarayanan Chandrasekharan, Karina Gomez, Akram Al-Hourani +8

Providing "connectivity from the sky" is the new innovative trend in wireless communications. High and low altitude platforms, drones, aircrafts and airships are being considered a…

cs.NI2016★ 4 cited

Wi-Fi/WiGig Coordination for Optimal WiGig Concurrent Transmissions in Random Access Scenario

Ehab Mahmoud Mohamed, Kei Sakaguchi, Seiichi Sampei

Wireless Gigabit (WiGig) access points (APs) using 60 GHz unlicensed frequency band are considered as key enablers for future Gbps WLANs. Due to its short range transmission with h…