default search action
Wieland Brendel
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j8]Josue Ortega Caro, Yilong Ju
, Ryan Pyle, Sourav Dey, Wieland Brendel, Fabio Anselmi, Ankit B. Patel:
Translational symmetry in convolutions with localized kernels causes an implicit bias toward high frequency adversarial examples. Frontiers Comput. Neurosci. 18 (2024) - [c32]Goutham Rajendran, Patrik Reizinger, Wieland Brendel, Pradeep Kumar Ravikumar:
An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis. CLeaR 2024: 41-70 - [c31]Amro Abbas, Evgenia Rusak, Kushal Tirumala, Wieland Brendel, Kamalika Chaudhuri, Ari S. Morcos:
Effective pruning of web-scale datasets based on complexity of concept clusters. ICLR 2024 - [c30]Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel:
Does CLIP's generalization performance mainly stem from high train-test similarity? ICLR 2024 - [c29]Thaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel:
Provable Compositional Generalization for Object-Centric Learning. ICLR 2024 - [c28]Robert Geirhos, Roland S. Zimmermann, Blair L. Bilodeau, Wieland Brendel, Been Kim:
Don't trust your eyes: on the (un)reliability of feature visualizations. ICML 2024 - [c27]Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár:
Position: Understanding LLMs Requires More Than Statistical Generalization. ICML 2024 - [i47]Amro Abbas, Evgenia Rusak, Kushal Tirumala, Wieland Brendel, Kamalika Chaudhuri, Ari S. Morcos:
Effective pruning of web-scale datasets based on complexity of concept clusters. CoRR abs/2401.04578 (2024) - [i46]Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár:
Understanding LLMs Requires More Than Statistical Generalization. CoRR abs/2405.01964 (2024) - [i45]Patrik Reizinger, Siyuan Guo, Ferenc Huszár, Bernhard Schölkopf, Wieland Brendel:
Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning. CoRR abs/2406.14302 (2024) - [i44]Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel:
InfoNCE: Identifying the Gap Between Theory and Practice. CoRR abs/2407.00143 (2024) - [i43]Anna Mészáros, Szilvia Ujváry, Wieland Brendel, Patrik Reizinger, Ferenc Huszár:
Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts. CoRR abs/2409.13728 (2024) - [i42]Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel:
In Search of Forgotten Domain Generalization. CoRR abs/2410.08258 (2024) - [i41]Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David A. Klindt:
Cross-Entropy Is All You Need To Invert the Data Generating Process. CoRR abs/2410.21869 (2024) - 2023
- [j7]Zhe Li
Robust deep learning object recognition models rely on low frequency information in natural images. PLoS Comput. Biol. 19(3) (2023) - [j6]Patrik Reizinger, Yash Sharma, Matthias Bethge, Bernhard Schölkopf, Ferenc Huszár, Wieland Brendel:
Jacobian-based Causal Discovery with Nonlinear ICA. Trans. Mach. Learn. Res. 2023 (2023) - [c26]Dejana Mandic, Wieland Brendel, Claudio Michaelis:
Iterative weakly supervised learning for novel class object detection. Tiny Papers @ ICLR 2023 - [c25]Jack Brady, Roland S. Zimmermann, Yash Sharma, Bernhard Schölkopf, Julius von Kügelgen, Wieland Brendel:
Provably Learning Object-Centric Representations. ICML 2023: 3038-3062 - [c24]Thaddäus Wiedemer, Prasanna Mayilvahanan, Matthias Bethge, Wieland Brendel:
Compositional Generalization from First Principles. NeurIPS 2023 - [c23]Roland S. Zimmermann, Thomas Klein, Wieland Brendel:
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models. NeurIPS 2023 - [d3]Patrik Reizinger
nl-causal-representations. Version v1.0.1. Zenodo, 2023 [all versions] - [i40]Jack Brady, Roland S. Zimmermann, Yash Sharma, Bernhard Schölkopf, Julius von Kügelgen, Wieland Brendel:
Provably Learning Object-Centric Representations. CoRR abs/2305.14229 (2023) - [i39]Robert Geirhos, Roland S. Zimmermann, Blair L. Bilodeau, Wieland Brendel, Been Kim:
Don't trust your eyes: on the (un)reliability of feature visualizations. CoRR abs/2306.04719 (2023) - [i38]Roland S. Zimmermann, Thomas Klein, Wieland Brendel:
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models. CoRR abs/2307.05471 (2023) - [i37]Thaddäus Wiedemer
Compositional Generalization from First Principles. CoRR abs/2307.05596 (2023) - [i36]Thaddäus Wiedemer
Provable Compositional Generalization for Object-Centric Learning. CoRR abs/2310.05327 (2023) - [i35]Prasanna Mayilvahanan, Thaddäus Wiedemer
Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity? CoRR abs/2310.09562 (2023) - [i34]Goutham Rajendran, Patrik Reizinger, Wieland Brendel, Pradeep Ravikumar:
An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis. CoRR abs/2311.18048 (2023) - 2022
- [j5]Evgenia Rusak, Steffen Schneider, George Pachitariu, Luisa Eck, Peter Vincent Gehler, Oliver Bringmann, Wieland Brendel, Matthias Bethge:
If your data distribution shifts, use self-learning. Trans. Mach. Learn. Res. 2022 (2022) - [c22]Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter Vincent Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel:
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain. ICLR 2022 - [c21]Patrik Reizinger, Luigi Gresele, Jack Brady, Julius von Kügelgen, Dominik Zietlow, Bernhard Schölkopf, Georg Martius, Wieland Brendel, Michel Besserve:
Embrace the Gap: VAEs Perform Independent Mechanism Analysis. NeurIPS 2022 - [c20]Roland S. Zimmermann, Wieland Brendel, Florian Tramèr, Nicholas Carlini:
Increasing Confidence in Adversarial Robustness Evaluations. NeurIPS 2022 - [d2]Patrik Reizinger
ima-vae. Zenodo, 2022 - [d1]Patrik Reizinger
nl-causal-representations. Version 1.0.0. Zenodo, 2022 [all versions] - [i33]Patrik Reizinger, Luigi Gresele, Jack Brady, Julius von Kügelgen, Dominik Zietlow, Bernhard Schölkopf, Georg Martius, Wieland Brendel, Michel Besserve:
Embrace the Gap: VAEs Perform Independent Mechanism Analysis. CoRR abs/2206.02416 (2022) - [i32]Roland S. Zimmermann, Wieland Brendel, Florian Tramèr
Increasing Confidence in Adversarial Robustness Evaluations. CoRR abs/2206.13991 (2022) - 2021
- [j4]Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker:
Benchmarking Unsupervised Object Representations for Video Sequences. J. Mach. Learn. Res. 22: 183:1-183:61 (2021) - [c19]Judy Borowski, Roland Simon Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel:
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization. ICLR 2021 - [c18]David A. Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, Dylan M. Paiton:
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding. ICLR 2021 - [c17]Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel:
Contrastive Learning Inverts the Data Generating Process. ICML 2021: 12979-12990 - [c16]Roland S. Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge, Thomas S. A. Wallis, Wieland Brendel:
How Well do Feature Visualizations Support Causal Understanding of CNN Activations? NeurIPS 2021: 11730-11744 - [c15]Julius von Kügelgen, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Schölkopf, Michel Besserve, Francesco Locatello:
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style. NeurIPS 2021: 16451-16467 - [c14]Maura Pintor, Fabio Roli, Wieland Brendel, Battista Biggio:
Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints. NeurIPS 2021: 20052-20062 - [c13]Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Tizian Thieringer, Matthias Bethge, Felix A. Wichmann, Wieland Brendel:
Partial success in closing the gap between human and machine vision. NeurIPS 2021: 23885-23899 - [i31]Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel:
Contrastive Learning Inverts the Data Generating Process. CoRR abs/2102.08850 (2021) - [i30]Maura Pintor, Fabio Roli, Wieland Brendel, Battista Biggio:
Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints. CoRR abs/2102.12827 (2021) - [i29]Evgenia Rusak, Steffen Schneider, Peter V. Gehler, Oliver Bringmann, Wieland Brendel, Matthias Bethge:
Adapting ImageNet-scale models to complex distribution shifts with self-learning. CoRR abs/2104.12928 (2021) - [i28]Julius von Kügelgen, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Schölkopf, Michel Besserve, Francesco Locatello:
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style. CoRR abs/2106.04619 (2021) - [i27]Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Tizian Thieringer, Matthias Bethge, Felix A. Wichmann, Wieland Brendel:
Partial success in closing the gap between human and machine vision. CoRR abs/2106.07411 (2021) - [i26]Roland S. Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge, Thomas S. A. Wallis, Wieland Brendel:
How Well do Feature Visualizations Support Causal Understanding of CNN Activations? CoRR abs/2106.12447 (2021) - [i25]Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter V. Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel:
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain. CoRR abs/2107.08221 (2021) - 2020
- [j3]Jonas Rauber
Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX. J. Open Source Softw. 5(53): 2607 (2020) - [j2]Robert Geirhos
Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11): 665-673 (2020) - [j1]Wieland Brendel, Ralph Bourdoukan
Learning to represent signals spike by spike. PLoS Comput. Biol. 16(3) (2020) - [c12]Evgenia Rusak, Lukas Schott, Roland S. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge, Wieland Brendel:
A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions. ECCV (3) 2020: 53-69 - [c11]Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann, Wieland Brendel, Matthias Bethge:
Improving robustness against common corruptions by covariate shift adaptation. NeurIPS 2020 - [c10]Florian Tramèr
On Adaptive Attacks to Adversarial Example Defenses. NeurIPS 2020 - [i24]Evgenia Rusak, Lukas Schott, Roland S. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge, Wieland Brendel:
Increasing the robustness of DNNs against image corruptions by playing the Game of Noise. CoRR abs/2001.06057 (2020) - [i23]Florian Tramèr, Nicholas Carlini, Wieland Brendel, Aleksander Madry:
On Adaptive Attacks to Adversarial Example Defenses. CoRR abs/2002.08347 (2020) - [i22]Robert Geirhos
Shortcut Learning in Deep Neural Networks. CoRR abs/2004.07780 (2020) - [i21]Christina M. Funke, Judy Borowski, Karolina Stosio, Wieland Brendel, Thomas S. A. Wallis, Matthias Bethge:
The Notorious Difficulty of Comparing Human and Machine Perception. CoRR abs/2004.09406 (2020) - [i20]Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker
Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences. CoRR abs/2006.07034 (2020) - [i19]Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann, Wieland Brendel, Matthias Bethge:
Improving robustness against common corruptions by covariate shift adaptation. CoRR abs/2006.16971 (2020) - [i18]David A. Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, Dylan M. Paiton:
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding. CoRR abs/2007.10930 (2020) - [i17]Jonas Rauber, Matthias Bethge, Wieland Brendel:
EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy. CoRR abs/2008.04175 (2020) - [i16]Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Matthias Bethge, Felix A. Wichmann, Wieland Brendel:
On the surprising similarities between supervised and self-supervised models. CoRR abs/2010.08377 (2020) - [i15]Judy Borowski, Roland S. Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel:
Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations. CoRR abs/2010.12606 (2020)
2010 – 2019
- 2019
- [c9]Wieland Brendel, Matthias Bethge:
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet. ICLR (Poster) 2019 - [c8]Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, Wieland Brendel:
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. ICLR 2019 - [c7]Lukas Schott, Jonas Rauber, Matthias Bethge, Wieland Brendel:
Towards the first adversarially robust neural network model on MNIST. ICLR (Poster) 2019 - [c6]Zhe Li, Wieland Brendel, Edgar Y. Walker, Erick Cobos, Taliah Muhammad, Jacob Reimer, Matthias Bethge, Fabian H. Sinz, Xaq Pitkow, Andreas S. Tolias:
Learning from brains how to regularize machines. NeurIPS 2019: 9525-9535 - [c5]Wieland Brendel, Jonas Rauber, Matthias Kümmerer, Ivan Ustyuzhaninov, Matthias Bethge:
Accurate, reliable and fast robustness evaluation. NeurIPS 2019: 12841-12851 - [i14]Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian J. Goodfellow, Aleksander Madry, Alexey Kurakin:
On Evaluating Adversarial Robustness. CoRR abs/1902.06705 (2019) - [i13]Wieland Brendel, Matthias Bethge:
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet. CoRR abs/1904.00760 (2019) - [i12]Wieland Brendel, Jonas Rauber, Matthias Kümmerer, Ivan Ustyuzhaninov, Matthias Bethge:
Accurate, reliable and fast robustness evaluation. CoRR abs/1907.01003 (2019) - [i11]Claudio Michaelis, Benjamin Mitzkus, Robert Geirhos, Evgenia Rusak, Oliver Bringmann, Alexander S. Ecker
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming. CoRR abs/1907.07484 (2019) - [i10]Zhe Li
Learning From Brains How to Regularize Machines. CoRR abs/1911.05072 (2019) - 2018
- [c4]Wieland Brendel, Jonas Rauber, Matthias Bethge:
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models. ICLR (Poster) 2018 - [i9]Alexander Böttcher, Wieland Brendel, Bernhard Englitz, Matthias Bethge:
Trace your sources in large-scale data: one ring to find them all. CoRR abs/1803.08882 (2018) - [i8]Lukas Schott, Jonas Rauber, Wieland Brendel, Matthias Bethge:
Robust Perception through Analysis by Synthesis. CoRR abs/1805.09190 (2018) - [i7]Ivan Ustyuzhaninov, Claudio Michaelis, Wieland Brendel, Matthias Bethge:
One-shot Texture Segmentation. CoRR abs/1807.02654 (2018) - [i6]Wieland Brendel, Jonas Rauber, Alexey Kurakin, Nicolas Papernot, Behar Veliqi, Marcel Salathé, Sharada P. Mohanty, Matthias Bethge:
Adversarial Vision Challenge. CoRR abs/1808.01976 (2018) - [i5]Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, Wieland Brendel:
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. CoRR abs/1811.12231 (2018) - 2017
- [c3]Ivan Ustyuzhaninov, Wieland Brendel, Leon A. Gatys, Matthias Bethge:
What does it take to generate natural textures? ICLR (Poster) 2017 - [i4]Wieland Brendel, Matthias Bethge:
Comment on "Biologically inspired protection of deep networks from adversarial attacks". CoRR abs/1704.01547 (2017) - [i3]Jonas Rauber, Wieland Brendel, Matthias Bethge:
Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models. CoRR abs/1707.04131 (2017) - [i2]Wieland Brendel, Jonas Rauber, Matthias Bethge:
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models. CoRR abs/1712.04248 (2017) - 2016
- [i1]Ivan Ustyuzhaninov, Wieland Brendel, Leon A. Gatys, Matthias Bethge:
Texture Synthesis Using Shallow Convolutional Networks with Random Filters. CoRR abs/1606.00021 (2016) - 2014
- [c2]Pietro Vertechi, Wieland Brendel, Christian K. Machens:
Unsupervised learning of an efficient short-term memory network. NIPS 2014: 3653-3661 - 2011
- [c1]Wieland Brendel, Ranulfo Romo, Christian K. Machens:
Demixed Principal Component Analysis. NIPS 2011: 2654-2662
Coauthor Index
[c30] [c29] [i42] [j7] [j6] [c24] [d3] [i37] [i36] [i35] [j5] [c22] [d1] [j4] [c19] [c18] [c17] [c16] [c13] [i31] [i29] [i27] [i26] [i25] [j3] [j2] [c12] [c11] [i24] [i22] [i21] [i20] [i19] [i18] [i17] [i16] [i15] [c9] [c8] [c7] [c6] [c5] [i13] [i12] [i11] [i10] [c4] [i9] [i8] [i7] [i6] [i5] [c3] [i4] [i3] [i2] [i1]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-01 00:18 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: