activity
20182022
most citedDo Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset

5 citations · 11 across the 4 of their papers we have counts for

collaborators

11 papers

cs.LG20223 cited

A Rigorous Study Of The Deep Taylor Decomposition

Leon Sixt, Tim Landgraf

Saliency methods attempt to explain deep neural networks by highlighting the most salient features of a sample. Some widely used methods are based on a theoretical framework called…

cs.LG20223 cited

DNNR: Differential Nearest Neighbors Regression

Youssef Nader, Leon Sixt, Tim Landgraf

K-nearest neighbors (KNN) is one of the earliest and most established algorithms in machine learning. For regression tasks, KNN averages the targets within a neighborhood which pos…

cs.LG20225 cited

Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset

Leon Sixt, Martin Schuessler, Oana-Iuliana Popescu +2

A variety of methods exist to explain image classification models. However, whether they provide any benefit to users over simply comparing various inputs and the model's respectiv…

physics.bio-ph2021

Impact of Variable Speed on Collective Movement of Animal Groups

Pascal P. Klamser, Luis Gómez-Nava, Tim Landgraf +3

A variety of agent-based models has been proposed to account for the emergence of coordinated collective behavior of animal groups from simple interaction rules. A common, simplify…

cs.RO2020

Socially competent robots: adaptation improves leadership performance in groups of live fish

Tim Landgraf, Hauke J. Moenck, Gregor H. W. Gebhardt +6

Collective motion is commonly modeled with simple interaction rules between agents. Yet in nature, numerous observables vary within and between individuals and it remains largely u…

stat.ML2020

Restricting the Flow: Information Bottlenecks for Attribution

Karl Schulz, Leon Sixt, Federico Tombari +1

Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to…