activity
20172020
most citedMulti-Task Learning for Segmentation of Building Footprints with Deep Neural Networks

40 citations · 45 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG20205 cited

Training Deep Neural Networks Without Batch Normalization

Divya Gaur, Joachim Folz, Andreas Dengel

Training neural networks is an optimization problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been develope…

cs.CV2020

P NP, at least in Visual Question Answering

Shailza Jolly, Sebastian Palacio, Joachim Folz +3

In recent years, progress in the Visual Question Answering (VQA) field has largely been driven by public challenges and large datasets. One of the most widely-used of these is the…

cs.CV2018

What do Deep Networks Like to See?

Sebastian Palacio, Joachim Folz, Jörn Hees +3

We propose a novel way to measure and understand convolutional neural networks by quantifying the amount of input signal they let in. To do this, an autoencoder (AE) was fine-tuned…

cs.LG2018

Adversarial Defense based on Structure-to-Signal Autoencoders

Joachim Folz, Sebastian Palacio, Joern Hees +2

Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerou…

cs.CV201740 cited

Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks

Benjamin Bischke, Patrick Helber, Joachim Folz +2

The increased availability of high resolution satellite imagery allows to sense very detailed structures on the surface of our planet. Access to such information opens up new direc…