Matthias Hein
Artificial Intelligence · 2004–2021
A researcher in the Science corpus: 35 papers; trusts 3,085 researchers and is trusted by 1,438 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 859 citations into it; #1,264 of 36,961 by trust here, #1,705 by citations
- Computer Vision and Pattern Recognition — 479 citations into it; #1,731 of 21,973 by trust here, #2,462 by citations
- Safety, Robustness & Interpretability — 415 citations into it; #90 of 2,259 by trust here, #331 by citations
- Optimization & Training — 120 citations into it
- Signal Processing — 97 citations into it; #459 of 7,592 by trust here, #1,122 by citations
- Model Architectures — 77 citations into it
- Representation & Self-Supervised Learning — 77 citations into it; #1,740 of 3,156 by trust here, #1,338 by citations
- Computational Mechanics — 75 citations into it; #3,279 of 10,021 by trust here, #3,038 by citations
Whom Matthias Hein trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Christian Szegedy
- Diederik P. Kingma
- Yoshua Bengio
- Ian J. Goodfellow
- Yann LeCun
- Ilya Sutskever
- Karen Simonyan
Who trusts Matthias Hein overall
- Francesco Croce
- Maksym Andriushchenko
- Huan Zhang
- David Stutz
- Bernt Schiele
- Andrea Vedaldi
- Tianyu Pang
- Krikamol Muandet
- Simon Shaolei Du
- Bernhard Schölkopf
Papers from Matthias Hein's perspective
Ordered by how strongly the researchers Matthias Hein trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Simple Does It: Weakly Supervised Instance and Semantic Segmentation (2016) — 795 citations
- Latent Embeddings for Zero-Shot Classification (2016) — 750 citations
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation (2017) — 553 citations
- Hilbertian Metrics and Positive Definite Kernels on Probability Measures (2005) — 231 citations
- Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem (2018) — 630 citations
- The Loss Surface of Deep and Wide Neural Networks (2017) — 306 citations
- Disentangling Adversarial Robustness and Generalization (2018) — 329 citations
- Weakly Supervised Object Boundaries (2015) — 46 citations
- Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks (2020) — 2,457 citations
- Scalable Multitask Representation Learning for Scene Classification (2014) — 57 citations
- Learning using privileged information: SV M+ and weighted SVM (2013) — 142 citations
- Provable Robustness of ReLU networks via Maximization of Linear Regions (2018) — 173 citations
- RobustBench: a standardized adversarial robustness benchmark (2020) — 928 citations
- Towards neural networks that provably know when they don't know (2019) — 151 citations
- Constrained 1-Spectral Clustering (2012) — 89 citations
- Loss Functions for Top-k Error: Analysis and Insights (2015) — 110 citations
- Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks (2020) — 365 citations
- Square Attack: a query-efficient black-box adversarial attack via random search (2019) — 1,300 citations
- Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack (2019) — 615 citations
- From Graphs to Manifolds - Weak and Strong Pointwise Consistency of Graph Laplacians (2005) — 369 citations