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