activity
20152022
most citedRecovering Localized Adversarial Attacks

2 citations · 5 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV20222 cited

Addressing Data Scarcity in Multimodal User State Recognition by Combining Semi-Supervised and Supervised Learning

Hendric Voß, Heiko Wersing, Stefan Kopp

Detecting mental states of human users is crucial for the development of cooperative and intelligent robots, as it enables the robot to understand the user's intentions and desires…

cs.HC2020

Intuitiveness in Active Teaching

Jan Philip Göpfert, Ulrike Kuhl, Lukas Hindemith +2

While Machine learning gives rise to astonishing results in automated systems, it is usually at the cost of large data requirements. This makes many successful algorithms from mach…

cs.LG2020

Interpretable Locally Adaptive Nearest Neighbors

Jan Philip Göpfert, Heiko Wersing, Barbara Hammer

When training automated systems, it has been shown to be beneficial to adapt the representation of data by learning a problem-specific metric. This metric is global. We extend this…

cs.LG20192 cited

Recovering Localized Adversarial Attacks

Jan Philip Göpfert, Heiko Wersing, Barbara Hammer

Deep convolutional neural networks have achieved great successes over recent years, particularly in the domain of computer vision. They are fast, convenient, and -- thanks to matur…

cs.LG2019

Adversarial attacks hidden in plain sight

Jan Philip Göpfert, André Artelt, Heiko Wersing +1

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples…

cs.LG20151 cited

Optimum Reject Options for Prototype-based Classification

Lydia Fischer, Barbara Hammer, Heiko Wersing

We analyse optimum reject strategies for prototype-based classifiers and real-valued rejection measures, using the distance of a data point to the closest prototype or probabilisti…