Felix Wichmann

Computer Vision and Pattern Recognition · 2001–2021

A researcher in the Science corpus: 16 papers; trusts 425 researchers and is trusted by 61 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 221 citations into it; #5,662 of 21,575 by trust here, #2,814 by citations
• Artificial Intelligence — 205 citations into it; #24,154 of 35,345 by trust here, #7,858 by citations
• Cognitive Neuroscience — 88 citations into it; #2,267 of 10,852 by trust here, #606 by citations
• Safety, Robustness & Interpretability — 56 citations into it; #1,045 of 2,251 by trust here, #229 by citations
• Evaluation & Benchmarks — 46 citations into it
• Statistics and Probability — 43 citations into it; #2,314 of 12,932 by trust here, #3,703 by citations
• Neuroscience — 32 citations into it; #364 of 487 by trust here, #444 by citations
• Model Architectures — 30 citations into it

Whom Felix Wichmann trusts overall

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

1. Bradley Efron
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Kaiming He
5. Tomaso A. Poggio
6. Karen Simonyan
7. Eero P. Simoncelli
8. Christian Szegedy
9. George A. Miller
10. Yoshua Bengio

Who trusts Felix Wichmann overall

1. Robert Geirhos
2. Cesare V. Parise
3. Gerrit W. Maus
4. Heiko H. Schütt
5. David M. Hoffman
6. Hannah B. Helbig
7. Miguel A. García-Pérez
8. Marc O. Ernst
9. Yuki Yamada
10. Jason Fischer

Papers from Felix Wichmann's perspective

Ordered by how strongly the researchers Felix Wichmann 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. Attention is All you Need (Neural Information Processing Systems)
5. Gradient-based learning applied to document recognition
6. ImageNet: A large-scale hierarchical image database
7. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
8. Long Short-Term Memory
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
• Shortcut learning in deep neural networks (2020) — 3,155 citations
• Comparing deep neural networks against humans: object recognition when the signal gets weaker (2017) — 253 citations
• Testing models of peripheral encoding using metamerism in an oddity paradigm. (2016) — 46 citations
• Partial success in closing the gap between human and machine vision (2021) — 298 citations
• An overview of quantitative approaches in Gestalt perception. (2016) — 72 citations
• Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency (2020) — 150 citations
• A parametric texture model based on deep convolutional features closely matches texture appearance for humans (2017) — 63 citations
• Animal detection in natural scenes: critical features revisited. (2010) — 58 citations
• Generalization and similarity in exemplar models of categorization: Insights from machine learning (2008) — 73 citations
• The psychometric function: II. Bootstrap-based confidence intervals and sampling (2001) — 870 citations
• The psychometric function: I. Fitting, sampling, and goodness of fit (2001) — 1,703 citations
• How Sensitive Is the Human Visual System to the Local Statistics of Natural Images? (2013) — 71 citations
• Generalisation in humans and deep neural networks (2018) — 685 citations
• Painfree and accurate Bayesian estimation of psychometric functions for (potentially) overdispersed data. (2016) — 375 citations
• The psychometric function: I (2001) — 980 citations