54 citations · 247 across the 13 of their papers we have counts for
4 papers · 1 filter
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…
When Explanations Lie: Why Many Modified BP Attributions Fail
Leon Sixt, Maximilian Granz, Tim Landgraf
Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score…