Antti Tarvainen

Artificial Intelligence · 2017

A researcher in the Science corpus: 2 papers; trusts 58 researchers and is trusted by 357 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 39 citations into it; #2,649 of 35,345 by trust here, #7,062 by citations
• Computer Vision and Pattern Recognition — 27 citations into it; #2,678 of 21,575 by trust here, #5,082 by citations
• Optimization & Training — 17 citations into it; #137 of 2,601 by trust here, #293 by citations
• Representation & Self-Supervised Learning — 13 citations into it; #227 of 3,145 by trust here, #607 by citations
• Efficiency & Compression — 8 citations into it
• Model Architectures — 8 citations into it
• Generative Models — 6 citations into it
• Safety, Robustness & Interpretability — 6 citations into it

Whom Antti Tarvainen trusts overall

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

1. Alex Krizhevsky
2. Diederik P. Kingma
3. Geoffrey E. Hinton
4. Tim Salimans
5. Christian Szegedy
6. Sergey Ioffe
7. Ian J. Goodfellow
8. Yoshua Bengio
9. Individualized Treat
10. Jimmy Ba

Who trusts Antti Tarvainen overall

1. Lukas Hoyer
2. Ekin Dogus Cubuk
3. Lu Liu
4. Yassine Ouali
5. Luc Van Gool
6. Kai Han
7. Geoff French
8. Jiaao Chen
9. Quoc V. Le
10. Ben Athiwaratkun

Papers from Antti Tarvainen's perspective

Ordered by how strongly the researchers Antti Tarvainen 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. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Weight-averaged consistency targets improve semi-supervised deep learning results (2017) — 1,218 citations
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results (2017) — 5,726 citations