Robert Geirhos

Computer Vision and Pattern Recognition · 2017–2023

A researcher in the Science corpus: 9 papers; trusts 553 researchers and is trusted by 43 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 313 citations into it; #5,042 of 21,575 by trust here, #2,273 by citations
• Artificial Intelligence — 285 citations into it; #17,041 of 35,345 by trust here, #5,002 by citations
• Evaluation & Benchmarks — 79 citations into it
• Safety, Robustness & Interpretability — 76 citations into it; #1,122 of 2,251 by trust here, #229 by citations
• Representation & Self-Supervised Learning — 53 citations into it
• Cognitive Neuroscience — 50 citations into it; #2,826 of 10,852 by trust here, #679 by citations
• Model Architectures — 41 citations into it
• Natural Language Processing — 27 citations into it

Whom Robert Geirhos trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Kaiming He
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Karen Simonyan
5. Yoshua Bengio
6. Christian Szegedy
7. Ilya Sutskever
8. Ross B. Girshick
9. Diederik P. Kingma
10. George A. Miller

Who trusts Robert Geirhos overall

1. Evgenia Rusak
2. Raphael Gontijo Lopes
3. Ben Sorscher
4. Hyeonseob Nam
5. Dan Hendrycks
6. Axel Sauer
7. Wieland Brendel
8. Katherine L. Hermann
9. Hyunjae Lee
10. Dong Yin

Papers from Robert Geirhos's perspective

Ordered by how strongly the researchers Robert Geirhos trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet: A large-scale hierarchical image database
5. Attention is All you Need (Neural Information Processing Systems)
6. Long Short-Term Memory
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (2018) — 3,222 citations
• Scaling Vision Transformers to 22 Billion Parameters (2023) — 911 citations
• Shortcut learning in deep neural networks (2020) — 3,155 citations
• Beyond neural scaling laws: beating power law scaling via data pruning (2022) — 656 citations
• Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming (2019) — 574 citations
• Comparing deep neural networks against humans: object recognition when the signal gets weaker (2017) — 253 citations
• Partial success in closing the gap between human and machine vision (2021) — 298 citations
• Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency (2020) — 150 citations
• Generalisation in humans and deep neural networks (2018) — 685 citations