Wieland Brendel

Orcid: 0000-0003-0982-552X

According to our database1, Wieland Brendel authored at least 64 papers between 2011 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Translational symmetry in convolutions with localized kernels causes an implicit bias toward high frequency adversarial examples.
Frontiers Comput. Neurosci., 2024

In Search of Forgotten Domain Generalization.
CoRR, 2024

Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts.
CoRR, 2024

InfoNCE: Identifying the Gap Between Theory and Practice.
CoRR, 2024

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning.
CoRR, 2024

Understanding LLMs Requires More Than Statistical Generalization.
CoRR, 2024

Position: Understanding LLMs Requires More Than Statistical Generalization.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Don't trust your eyes: on the (un)reliability of feature visualizations.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Provable Compositional Generalization for Object-Centric Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Does CLIP's generalization performance mainly stem from high train-test similarity?
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Effective pruning of web-scale datasets based on complexity of concept clusters.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis.
Proceedings of the Causal Learning and Reasoning, 2024

2023

Robust deep learning object recognition models rely on low frequency information in natural images.
PLoS Comput. Biol., March, 2023

Jacobian-based Causal Discovery with Nonlinear ICA.
Trans. Mach. Learn. Res., 2023

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Compositional Generalization from First Principles.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Provably Learning Object-Centric Representations.
Proceedings of the International Conference on Machine Learning, 2023

Iterative weakly supervised learning for novel class object detection.
Proceedings of the First Tiny Papers Track at ICLR 2023, 2023

2022


If your data distribution shifts, use self-learning.
Trans. Mach. Learn. Res., 2022

Increasing Confidence in Adversarial Robustness Evaluations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Embrace the Gap: VAEs Perform Independent Mechanism Analysis.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Benchmarking Unsupervised Object Representations for Video Sequences.
J. Mach. Learn. Res., 2021

Adapting ImageNet-scale models to complex distribution shifts with self-learning.
CoRR, 2021

How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Partial success in closing the gap between human and machine vision.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Contrastive Learning Inverts the Data Generating Process.
Proceedings of the 38th International Conference on Machine Learning, 2021

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding.
Proceedings of the 9th International Conference on Learning Representations, 2021

Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization.
Proceedings of the 9th International Conference on Learning Representations, 2021

2020
Learning to represent signals spike by spike.
PLoS Comput. Biol., 2020

Shortcut learning in deep neural networks.
Nat. Mach. Intell., 2020

Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX.
J. Open Source Softw., 2020

Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations.
CoRR, 2020

On the surprising similarities between supervised and self-supervised models.
CoRR, 2020

EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy.
CoRR, 2020

Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences.
CoRR, 2020

The Notorious Difficulty of Comparing Human and Machine Perception.
CoRR, 2020

Increasing the robustness of DNNs against image corruptions by playing the Game of Noise.
CoRR, 2020

On Adaptive Attacks to Adversarial Example Defenses.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Improving robustness against common corruptions by covariate shift adaptation.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions.
Proceedings of the Computer Vision - ECCV 2020, 2020

2019
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming.
CoRR, 2019

On Evaluating Adversarial Robustness.
CoRR, 2019

Accurate, reliable and fast robustness evaluation.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning from brains how to regularize machines.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Towards the first adversarially robust neural network model on MNIST.
Proceedings of the 7th International Conference on Learning Representations, 2019

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness.
Proceedings of the 7th International Conference on Learning Representations, 2019

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet.
Proceedings of the 7th International Conference on Learning Representations, 2019

2018
Adversarial Vision Challenge.
CoRR, 2018

One-shot Texture Segmentation.
CoRR, 2018

Robust Perception through Analysis by Synthesis.
CoRR, 2018

Trace your sources in large-scale data: one ring to find them all.
CoRR, 2018

Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models.
Proceedings of the 6th International Conference on Learning Representations, 2018

2017
Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models.
CoRR, 2017

Comment on "Biologically inspired protection of deep networks from adversarial attacks".
CoRR, 2017

What does it take to generate natural textures?
Proceedings of the 5th International Conference on Learning Representations, 2017

2016
Texture Synthesis Using Shallow Convolutional Networks with Random Filters.
CoRR, 2016

2014
Unsupervised learning of an efficient short-term memory network.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

2011
Demixed Principal Component Analysis.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011


  Loading...