Matthias Bethge
Computer Vision and Pattern Recognition · 2009–2023
A researcher in the Science corpus: 53 papers; trusts 3,059 researchers and is trusted by 9,558 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 991 citations into it; #291 of 21,973 by trust here, #366 by citations
- Artificial Intelligence — 861 citations into it; #1,402 of 36,961 by trust here, #2,099 by citations
- Safety, Robustness & Interpretability — 251 citations into it; #95 of 2,259 by trust here, #97 by citations
- Cognitive Neuroscience — 236 citations into it; #204 of 11,026 by trust here, #212 by citations
- Representation & Self-Supervised Learning — 208 citations into it; #3,090 of 3,156 by trust here, #2,497 by citations
- Model Architectures — 134 citations into it
- Evaluation & Benchmarks — 118 citations into it; #229 of 3,155 by trust here, #336 by citations
- Generative Models — 109 citations into it; #49 of 1,963 by trust here, #91 by citations
Whom Matthias Bethge trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Yoshua Bengio
- Karen Simonyan
- Yann LeCun
- Ilya Sutskever
- Ross B. Girshick
- Christian Szegedy
Who trusts Matthias Bethge overall
- Yoshua Bengio
- Andrea Vedaldi
- Wieland Brendel
- Aäron van den Oord
- Lucas Theis
- Florian Tramèr
- Robert Geirhos
- Nicholas Carlini
- Sergey Levine
- Jun-Yan Zhu
Papers from Matthias Bethge's perspective
Ordered by how strongly the researchers Matthias Bethge trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Image Style Transfer Using Convolutional Neural Networks (2016) — 5,793 citations
- A note on the evaluation of generative models (2015) — 1,233 citations
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (2018) — 3,222 citations
- A Neural Algorithm of Artistic Style (2015) — 3,091 citations
- Generative Image Modeling Using Spatial LSTMs (2015) — 208 citations
- Shortcut learning in deep neural networks (2020) — 3,155 citations
- Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet (2019) — 641 citations
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models (2017) — 1,559 citations
- Generalisation in humans and deep neural networks (2018) — 685 citations
- Controlling Perceptual Factors in Neural Style Transfer (2016) — 498 citations
- Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks (2015) — 132 citations
- Towards the first adversarially robust neural network model on MNIST (2018) — 391 citations
- Excessive Invariance Causes Adversarial Vulnerability (2018) — 174 citations
- Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models (2017) — 285 citations
- Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet (2014) — 446 citations
- Towards causal generative scene models via competition of experts (2020) — 54 citations
- Improving robustness against common corruptions by covariate shift adaptation (2020) — 651 citations
- A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions (2020) — 243 citations
- Partial success in closing the gap between human and machine vision (2021) — 298 citations
- Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming (2019) — 574 citations