research
∙
07/11/2023
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
In light of the recent widespread adoption of AI systems, understanding ...
share
research
∙
07/10/2023
Compositional Generalization from First Principles
Leveraging the compositional nature of our world to expedite learning an...
research
∙
06/07/2023
Don't trust your eyes: on the (un)reliability of feature visualizations
How do neural networks extract patterns from pixels? Feature visualizati...
research
∙
05/23/2023
Provably Learning Object-Centric Representations
Learning structured representations of the visual world in terms of obje...
research
∙
06/28/2022
Increasing Confidence in Adversarial Robustness Evaluations
Hundreds of defenses have been proposed to make deep neural networks rob...
research
∙
06/06/2022
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Variational autoencoders (VAEs) are a popular framework for modeling com...
research
∙
07/17/2021
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
An important component for generalization in machine learning is to unco...
research
∙
06/23/2021
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
One widely used approach towards understanding the inner workings of dee...
research
∙
06/14/2021
Partial success in closing the gap between human and machine vision
A few years ago, the first CNN surpassed human performance on ImageNet. ...
research
∙
06/08/2021
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
Self-supervised representation learning has shown remarkable success in ...
research
∙
04/27/2021
Adapting ImageNet-scale models to complex distribution shifts with self-learning
While self-learning methods are an important component in many recent do...
research
∙
02/25/2021
Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
Evaluating adversarial robustness amounts to finding the minimum perturb...
research
∙
02/17/2021
Contrastive Learning Inverts the Data Generating Process
Contrastive learning has recently seen tremendous success in self-superv...
research
∙
10/23/2020
Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations
Feature visualizations such as synthetic maximally activating images are...
research
∙
10/16/2020
On the surprising similarities between supervised and self-supervised models
How do humans learn to acquire a powerful, flexible and robust represent...
research
∙
08/10/2020
EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy
EagerPy is a Python framework that lets you write code that automaticall...
research
∙
07/21/2020
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
We construct an unsupervised learning model that achieves nonlinear dise...
research
∙
06/30/2020
Improving robustness against common corruptions by covariate shift adaptation
Today's state-of-the-art machine vision models are vulnerable to image c...
research
∙
06/12/2020
Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences
Perceiving the world in terms of objects is a crucial prerequisite for r...
research
∙
04/20/2020
The Notorious Difficulty of Comparing Human and Machine Perception
With the rise of machines to human-level performance in complex recognit...
research
∙
04/16/2020
Shortcut Learning in Deep Neural Networks
Deep learning has triggered the current rise of artificial intelligence ...
research
∙
02/19/2020
On Adaptive Attacks to Adversarial Example Defenses
Adaptive attacks have (rightfully) become the de facto standard for eval...
research
∙
01/16/2020
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...
research
∙
11/11/2019
Learning From Brains How to Regularize Machines
Despite impressive performance on numerous visual tasks, Convolutional N...
research
∙
07/17/2019
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
The ability to detect objects regardless of image distortions or weather...
research
∙
07/01/2019
Accurate, reliable and fast robustness evaluation
Throughout the past five years, the susceptibility of neural networks to...
research
∙
02/18/2019
On Evaluating Adversarial Robustness
Correctly evaluating defenses against adversarial examples has proven to...
research
∙
11/29/2018
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Convolutional Neural Networks (CNNs) are commonly thought to recognise o...
research
∙
08/06/2018
Adversarial Vision Challenge
The NIPS 2018 Adversarial Vision Challenge is a competition to facilitat...
research
∙
07/07/2018
One-shot Texture Segmentation
We introduce one-shot texture segmentation: the task of segmenting an in...
research
∙
05/23/2018
Robust Perception through Analysis by Synthesis
The intriguing susceptibility of deep neural networks to minimal input p...
research
∙
03/23/2018
Trace your sources in large-scale data: one ring to find them all
An important preprocessing step in most data analysis pipelines aims to ...
research
∙
12/12/2017
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
Many machine learning algorithms are vulnerable to almost imperceptible ...
research
∙
07/13/2017
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...
research
∙
04/05/2017
Comment on "Biologically inspired protection of deep networks from adversarial attacks"
A recent paper suggests that Deep Neural Networks can be protected from ...
research
∙
05/31/2016
Texture Synthesis Using Shallow Convolutional Networks with Random Filters
Here we demonstrate that the feature space of random shallow convolution...
research
∙
10/22/2014