Michael Lam

Computer Vision and Pattern Recognition · with Soatto · 2019–2020

A researcher in the Science corpus: 3 papers; trusts 144 researchers and is trusted by 6 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 82 citations into it; #12,471 of 21,575 by trust here, #6,606 by citations
• Artificial Intelligence — 80 citations into it; #19,927 of 35,345 by trust here, #9,369 by citations
• Optimization & Training — 35 citations into it
• Representation & Self-Supervised Learning — 33 citations into it; #2,547 of 3,145 by trust here, #1,692 by citations
• Model Architectures — 15 citations into it
• Reinforcement Learning — 10 citations into it

Whom Michael Lam trusts overall

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

1. Alex Krizhevsky
2. Kaiming He
3. Diederik P. Kingma
4. Geoffrey E. Hinton
5. Yoshua Bengio
6. Ilya Sutskever
7. Yann LeCun
8. Ross B. Girshick
9. Shun-ichi Amari
10. Karen Simonyan

Who trusts Michael Lam overall

1. Cuong V Nguyen
2. Alessandro Achille
3. Andrew Kyle Lampinen
4. Tal Hassner
5. Anh Tuan Tran
6. James L. McClelland
7. K. J. Joseph
8. Michael Matena
9. Mehdi Abbana Bennani

Papers from Michael Lam's perspective

Ordered by how strongly the researchers Michael Lam 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. ImageNet: A large-scale hierarchical image database
6. Learning Multiple Layers of Features from Tiny Images
7. Attention is All you Need (Neural Information Processing Systems)
8. Long Short-Term Memory
9. ImageNet Large Scale Visual Recognition Challenge
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Task2Vec: Task Embedding for Meta-Learning (2019) — 377 citations
• Toward Understanding Catastrophic Forgetting in Continual Learning (2019) — 124 citations
• Rethinking the Hyperparameters for Fine-tuning (2020) — 148 citations