most citedExplaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation

48 citations · 119 across the 5 of their papers we have counts for

collaborators

5 papers

eess.IV20201 cited

Blind Image Restoration with Flow Based Priors

Leonhard Helminger, Michael Bernasconi, Abdelaziz Djelouah +2

Image restoration has seen great progress in the last years thanks to the advances in deep neural networks. Most of these existing techniques are trained using full supervision wit…

cs.CV202022 cited

Lossy Image Compression with Normalizing Flows

Leonhard Helminger, Abdelaziz Djelouah, Markus Gross +1

Deep learning based image compression has recently witnessed exciting progress and in some cases even managed to surpass transform coding based approaches that have been establishe…

cs.LG20206 cited

Shapley Value as Principled Metric for Structured Network Pruning

Marco Ancona, Cengiz Öztireli, Markus Gross

Structured pruning is a well-known technique to reduce the storage size and inference cost of neural networks. The usual pruning pipeline consists of ranking the network internal f…

cs.GR202042 cited

Lagrangian Neural Style Transfer for Fluids

Byungsoo Kim, Vinicius C. Azevedo, Markus Gross +1

Artistically controlling the shape, motion and appearance of fluid simulations pose major challenges in visual effects production. In this paper, we present a neural style transfer…

cs.LG201948 cited

Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation

Marco Ancona, Cengiz Öztireli, Markus Gross

The problem of explaining the behavior of deep neural networks has recently gained a lot of attention. While several attribution methods have been proposed, most come without stron…