Zhaobai Zhong

Artificial Intelligence · 2017–2021

A researcher in the Science corpus: 6 papers; trusts 849 researchers and is trusted by 135 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 166 citations into it; #4,737 of 35,345 by trust here, #5,424 by citations
• Computer Vision and Pattern Recognition — 163 citations into it; #2,980 of 21,575 by trust here, #3,827 by citations
• Model Architectures — 87 citations into it
• Optimization & Training — 64 citations into it
• Neural Architecture Search & AutoML — 34 citations into it; #36 of 283 by trust here, #41 by citations
• Reinforcement Learning — 25 citations into it; #675 of 2,242 by trust here, #1,174 by citations
• Efficiency & Compression — 14 citations into it
• Evaluation & Benchmarks — 11 citations into it

Whom Zhaobai Zhong trusts overall

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

1. Kaiming He
2. Alex Krizhevsky
3. Christian Szegedy
4. Geoffrey E. Hinton
5. Karen Simonyan
6. Diederik P. Kingma
7. X. Zhang
8. Ross B. Girshick
9. Shaoqing Ren
10. Ilya Sutskever

Who trusts Zhaobai Zhong overall

1. Martin Wistuba
2. Yanan Sun
3. Hanxiao Liu
4. Yihui He
5. Han Cai
6. Thomas Elsken
7. Bing Xue
8. Qiang Wang
9. Song Han
10. Purushotham Kamath

Papers from Zhaobai Zhong's perspective

Ordered by how strongly the researchers Zhaobai Zhong 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. Long Short-Term Memory
5. ImageNet: A large-scale hierarchical image database
6. Attention is All you Need (Neural Information Processing Systems)
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

• Practical Network Blocks Design with Q-Learning (2017) — 127 citations
• Practical Block-Wise Neural Network Architecture Generation (2017) — 531 citations
• IRLAS: Inverse Reinforcement Learning for Architecture Search (2018) — 43 citations
• Adversarial AutoAugment (2019) — 215 citations
• BlockQNN: Efficient Block-Wise Neural Network Architecture Generation (2018) — 137 citations
• FixNorm: Dissecting Weight Decay for Training Deep Neural Networks (2021) — 6 citations