Lukas Schott — accepted AI-conference papers

2023

Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles

Martin Bjerke, Lukas Schott, Kristopher T Jensen, Claudia Battistin, David A. Klindt, Benjamin Adric Dunn

ICLR 2023poster

Systems neuroscience relies on two complementary views of neural data, characterized by single neuron tuning curves and analysis of population activity. These two perspectives combine elegantly in neural latent variable models that constrain the relationship between latent variables and neural activ…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗

2022

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

Lukas Schott, Julius Von Kügelgen, Frederik Träuble, Peter Vincent Gehler, Chris Russell, Matthias Bethge +3

ICLR 2022poster

An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the world. In this paper, we test whether 17 unsupervised, weakly supervised, and fully supervised representation learning app…

Cited by 81 Source ↗PDF ↗code ↗Scholar ↗

2021

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

David A. Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge +1

ICLR 2021oral

Disentangling the underlying generative factors from complex data has so far been limited to carefully constructed scenarios. We propose a path towards natural data by first showing that the statistics of natural data provide enough structure to enable disentanglement, both theoretically and empiric…

Cited by 154 Source ↗PDF ↗code ↗Scholar ↗

2020

A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions

Evgenia Rusak, Lukas Schott, Roland S. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge +1

ECCV 2020poster

The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image recognition models strongly degrades when evaluated on previously unseen corruptions. Here, we demonstrate that a simple…

Cited by 244 Source ↗PDF ↗code ↗Scholar ↗

2019

Towards the first adversarially robust neural network model on MNIST

Lukas Schott, Jonas Rauber, Matthias Bethge, Wieland Brendel

ICLR 2019poster

Despite much effort, deep neural networks remain highly susceptible to tiny input perturbations and even for MNIST, one of the most common toy datasets in computer vision, no neural network model exists for which adversarial perturbations are large and make semantic sense to humans. We show that eve…

Cited by 439 Source ↗PDF ↗Scholar ↗

2017

Deep learning on symbolic representations for large-scale heterogeneous time-series event prediction

Shengdong Zhang, Soheil Bahrampour, Naveen Ramakrishnan, Lukas Schott, Mohak Shah

ICASSP 2017accepted

In this paper, we consider the problem of event prediction with multi-variate time series data consisting of heterogeneous (continuous and categorical) variables. The complex dependencies between the variables combined with asynchronicity and sparsity of the data makes the event prediction problem p…

Cited by 0 Source ↗Scholar ↗

2017

Learned Watershed: End-To-End Learning of Seeded Segmentation

Steffen Wolf, Lukas Schott, Ullrich Kothe, Fred Hamprecht

ICCV 2017poster

Learned boundary maps are known to outperform hand-crafted ones as a basis for the watershed algorithm. We show, for the first time, how to train watershed computation jointly with boundary map prediction. The estimator for the merging priorities is cast as a neural network that is convolutional (ov…

Cited by 55 PDF ↗Scholar ↗