Matthias Bethge

verfied profile

Neuro- & Machine Learning Scientist, Professor at University of Tuebingen, Head of

Tuebingen AI Center, Co-Initiator of ELLIS, Co-Founder at DeepArt UG and Layer7 AI , Amazon Scholar, Researcher at UC Berkeley from 2003-2005.

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

An important component for generalization in machine learning is to unco...
07/17/2021 ∙ by Lukas Schott, et al. ∙ 14 ∙ share

read it
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?

One widely used approach towards understanding the inner workings of dee...
06/23/2021 ∙ by Roland S. Zimmermann, et al. ∙ 26 ∙ share

read it
Partial success in closing the gap between human and machine vision

A few years ago, the first CNN surpassed human performance on ImageNet. ...
06/14/2021 ∙ by Robert Geirhos, et al. ∙ 0 ∙ share

read it
Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling

Since 2014 transfer learning has become the key driver for the improveme...
05/26/2021 ∙ by Akis Linardos, et al. ∙ 11 ∙ share

read it
Adapting ImageNet-scale models to complex distribution shifts with self-learning

While self-learning methods are an important component in many recent do...
04/27/2021 ∙ by Evgenia Rusak, et al. ∙ 0 ∙ share

read it
State-of-the-Art in Human Scanpath Prediction

The last years have seen a surge in models predicting the scanpaths of f...
02/24/2021 ∙ by Matthias Kümmerer, et al. ∙ 25 ∙ share

read it
Contrastive Learning Inverts the Data Generating Process

Contrastive learning has recently seen tremendous success in self-superv...
02/17/2021 ∙ by Roland S. Zimmermann, et al. ∙ 8 ∙ share

read it
Closing the Generalization Gap in One-Shot Object Detection

Despite substantial progress in object detection and few-shot learning, ...
11/09/2020 ∙ by Claudio Michaelis, et al. ∙ 0 ∙ share

read it
Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations

Feature visualizations such as synthetic maximally activating images are...
10/23/2020 ∙ by Judy Borowski, et al. ∙ 13 ∙ share

read it
On the surprising similarities between supervised and self-supervised models

How do humans learn to acquire a powerful, flexible and robust represent...
10/16/2020 ∙ by Robert Geirhos, et al. ∙ 0 ∙ share

read it
EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy

EagerPy is a Python framework that lets you write code that automaticall...
08/10/2020 ∙ by Jonas Rauber, et al. ∙ 30 ∙ share

read it
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

We construct an unsupervised learning model that achieves nonlinear dise...
07/21/2020 ∙ by David Klindt, et al. ∙ 5 ∙ share

read it
Fast Differentiable Clipping-Aware Normalization and Rescaling

Rescaling a vector δ⃗∈ℝ^n to a desired length is a common operation in m...
07/15/2020 ∙ by Jonas Rauber, et al. ∙ 6 ∙ share

read it
Improving robustness against common corruptions by covariate shift adaptation

Today's state-of-the-art machine vision models are vulnerable to image c...
06/30/2020 ∙ by Steffen Schneider, et al. ∙ 5 ∙ share

read it
Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences

Perceiving the world in terms of objects is a crucial prerequisite for r...
06/12/2020 ∙ by Marissa A. Weis, et al. ∙ 14 ∙ share

read it
Towards causal generative scene models via competition of experts

Learning how to model complex scenes in a modular way with recombinable ...
04/27/2020 ∙ by Julius von Kugelgen, et al. ∙ 4 ∙ share

read it
The Notorious Difficulty of Comparing Human and Machine Perception

With the rise of machines to human-level performance in complex recognit...
04/20/2020 ∙ by Christina M. Funke, et al. ∙ 8 ∙ share

read it
Shortcut Learning in Deep Neural Networks

Deep learning has triggered the current rise of artificial intelligence ...
04/16/2020 ∙ by Robert Geirhos, et al. ∙ 3 ∙ share

read it
Increasing the robustness of DNNs against image corruptions by playing the Game of Noise

The human visual system is remarkably robust against a wide range of nat...
01/16/2020 ∙ by Evgenia Rusak, et al. ∙ 14 ∙ share

read it
Learning From Brains How to Regularize Machines

Despite impressive performance on numerous visual tasks, Convolutional N...
11/11/2019 ∙ by Zhe Li, et al. ∙ 36 ∙ share

read it
Pretraining boosts out-of-domain robustness for pose estimation

Deep neural networks are highly effective tools for human and animal pos...
09/24/2019 ∙ by Alexander Mathis, et al. ∙ 1 ∙ share

read it
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming

The ability to detect objects regardless of image distortions or weather...
07/17/2019 ∙ by Claudio Michaelis, et al. ∙ 4 ∙ share

read it
Accurate, reliable and fast robustness evaluation

Throughout the past five years, the susceptibility of neural networks to...
07/01/2019 ∙ by Wieland Brendel, et al. ∙ 3 ∙ share

read it
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

Convolutional Neural Networks (CNNs) are commonly thought to recognise o...
11/29/2018 ∙ by Robert Geirhos, et al. ∙ 14 ∙ share

read it
One-Shot Instance Segmentation

We tackle one-shot visual search by example for arbitrary object categor...
11/28/2018 ∙ by Claudio Michaelis, et al. ∙ 16 ∙ share

read it
Excessive Invariance Causes Adversarial Vulnerability

Despite their impressive performance, deep neural networks exhibit strik...
11/01/2018 ∙ by Jörn-Henrik Jacobsen, et al. ∙ 16 ∙ share

read it
A rotation-equivariant convolutional neural network model of primary visual cortex

Classical models describe primary visual cortex (V1) as a filter bank of...
09/27/2018 ∙ by Alexander S. Ecker, et al. ∙ 6 ∙ share

read it
Generalisation in humans and deep neural networks

We compare the robustness of humans and current convolutional deep neura...
08/27/2018 ∙ by Robert Geirhos, et al. ∙ 4 ∙ share

read it
Adversarial Vision Challenge

The NIPS 2018 Adversarial Vision Challenge is a competition to facilitat...
08/06/2018 ∙ by Wieland Brendel, et al. ∙ 4 ∙ share

read it
Diverse feature visualizations reveal invariances in early layers of deep neural networks

Visualizing features in deep neural networks (DNNs) can help understandi...
07/27/2018 ∙ by Santiago A. Cadena, et al. ∙ 2 ∙ share

read it
One-shot Texture Segmentation

We introduce one-shot texture segmentation: the task of segmenting an in...
07/07/2018 ∙ by Ivan Ustyuzhaninov, et al. ∙ 0 ∙ share

read it
Robust Perception through Analysis by Synthesis

The intriguing susceptibility of deep neural networks to minimal input p...
05/23/2018 ∙ by Lukas Schott, et al. ∙ 0 ∙ share

read it
Markerless tracking of user-defined features with deep learning

Quantifying behavior is crucial for many applications in neuroscience. V...
04/09/2018 ∙ by Alexander Mathis, et al. ∙ 2 ∙ share

read it
One-Shot Segmentation in Clutter

We tackle the problem of one-shot segmentation: finding and segmenting a...
03/26/2018 ∙ by Claudio Michaelis, et al. ∙ 0 ∙ share

read it
Trace your sources in large-scale data: one ring to find them all

An important preprocessing step in most data analysis pipelines aims to ...
03/23/2018 ∙ by Alexander Böttcher, et al. ∙ 0 ∙ share

read it
Guiding human gaze with convolutional neural networks

The eye fixation patterns of human observers are a fundamental indicator...
12/18/2017 ∙ by Leon A. Gatys, et al. ∙ 0 ∙ share

read it
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

Many machine learning algorithms are vulnerable to almost imperceptible ...
12/12/2017 ∙ by Wieland Brendel, et al. ∙ 0 ∙ share

read it
Neural system identification for large populations separating "what" and "where"

Neuroscientists classify neurons into different types that perform simil...
11/07/2017 ∙ by David A. Klindt, et al. ∙ 0 ∙ share

read it
Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models

Even todays most advanced machine learning models are easily fooled by a...
07/13/2017 ∙ by Jonas Rauber, et al. ∙ 0 ∙ share

read it
Comparing deep neural networks against humans: object recognition when the signal gets weaker

Human visual object recognition is typically rapid and seemingly effortl...
06/21/2017 ∙ by Robert Geirhos, et al. ∙ 0 ∙ share

read it
Comment on "Biologically inspired protection of deep networks from adversarial attacks"

A recent paper suggests that Deep Neural Networks can be protected from ...
04/05/2017 ∙ by Wieland Brendel, et al. ∙ 0 ∙ share

read it
Synthesising Dynamic Textures using Convolutional Neural Networks

Here we present a parametric model for dynamic textures. The model is ba...
02/22/2017 ∙ by Christina M. Funke, et al. ∙ 0 ∙ share

read it
Controlling Perceptual Factors in Neural Style Transfer

Neural Style Transfer has shown very exciting results enabling new forms...
11/23/2016 ∙ by Leon A. Gatys, et al. ∙ 0 ∙ share

read it
DeepGaze II: Reading fixations from deep features trained on object recognition

Here we present DeepGaze II, a model that predicts where people look in ...
10/05/2016 ∙ by Matthias Kümmerer, et al. ∙ 0 ∙ share

read it
Preserving Color in Neural Artistic Style Transfer

This note presents an extension to the neural artistic style transfer al...
06/19/2016 ∙ by Leon A. Gatys, et al. ∙ 0 ∙ share

read it
Texture Synthesis Using Shallow Convolutional Networks with Random Filters

Here we demonstrate that the feature space of random shallow convolution...
05/31/2016 ∙ by Ivan Ustyuzhaninov, et al. ∙ 0 ∙ share

read it
A note on the evaluation of generative models

Probabilistic generative models can be used for compression, denoising, ...
11/05/2015 ∙ by Lucas Theis, et al. ∙ 0 ∙ share

read it
A Neural Algorithm of Artistic Style

In fine art, especially painting, humans have mastered the skill to crea...
08/26/2015 ∙ by Leon A. Gatys, et al. ∙ 0 ∙ share

read it
Generative Image Modeling Using Spatial LSTMs

Modeling the distribution of natural images is challenging, partly becau...
06/10/2015 ∙ by Lucas Theis, et al. ∙ 0 ∙ share

read it
A Generative Model of Natural Texture Surrogates

Natural images can be viewed as patchworks of different textures, where ...
05/28/2015 ∙ by Niklas Ludtke, et al. ∙ 0 ∙ share

read it

Matthias Bethge

Featured Co-authors