149 citations · 338 across the 11 of their papers we have counts for
7 papers · 1 filter
DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling
Akis Linardos, Matthias Kümmerer, Ori Press +1
Since 2014 transfer learning has become the key driver for the improvement of spatial saliency prediction; however, with stagnant progress in the last 3-5 years. We conduct a large…
EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy
Jonas Rauber, Matthias Bethge, Wieland Brendel
EagerPy is a Python framework that lets you write code that automatically works natively with PyTorch, TensorFlow, JAX, and NumPy. Library developers no longer need to choose betwe…
Fast Differentiable Clipping-Aware Normalization and Rescaling
Jonas Rauber, Matthias Bethge
Rescaling a vector to a desired length is a common operation in many areas such as data science and machine learning. When the rescaled perturbation $η\vec…
Improving robustness against common corruptions by covariate shift adaptation
Steffen Schneider, Evgenia Rusak, Luisa Eck +3
Today's state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world application…
Learning From Brains How to Regularize Machines
Zhe Li, Wieland Brendel, Edgar Y. Walker +7
Despite impressive performance on numerous visual tasks, Convolutional Neural Networks (CNNs) --- unlike brains --- are often highly sensitive to small perturbations of their input…
Excessive Invariance Causes Adversarial Vulnerability
Jörn-Henrik Jacobsen, Jens Behrmann, Richard Zemel +1
Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neura…