Ekin Dogus Cubuk
Artificial Intelligence · 2014–2023
A researcher in the Science corpus: 32 papers; trusts 2,739 researchers and is trusted by 6,262 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 868 citations into it; #509 of 36,961 by trust here, #482 by citations
- Computer Vision and Pattern Recognition — 803 citations into it; #556 of 21,973 by trust here, #560 by citations
- Representation & Self-Supervised Learning — 220 citations into it; #357 of 3,156 by trust here, #229 by citations
- Model Architectures — 164 citations into it
- Optimization & Training — 160 citations into it; #240 of 2,605 by trust here, #120 by citations
- Materials Chemistry — 104 citations into it; #6,671 of 11,531 by trust here, #5,269 by citations
- Evaluation & Benchmarks — 98 citations into it
- Safety, Robustness & Interpretability — 95 citations into it; #411 of 2,259 by trust here, #415 by citations
Whom Ekin Dogus Cubuk trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Barret Zoph
- Ilya Sutskever
- Christian Szegedy
- Quoc V. Le
- Diederik P. Kingma
- Yoshua Bengio
- Ross B. Girshick
Who trusts Ekin Dogus Cubuk overall
- Quoc V. Le
- Raphael Gontijo Lopes
- Barret Zoph
- Ting-Li Chen
- Kihyuk Sohn
- Mingxing Tan
- Zizhao Zhang
- Yoshua Bengio
- Hugo Touvron
- Andrew Brock
Papers from Ekin Dogus Cubuk's perspective
Ordered by how strongly the researchers Ekin Dogus Cubuk trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Randaugment: Practical automated data augmentation with a reduced search space (2019) — 4,297 citations
- AutoAugment: Learning Augmentation Policies from Data (2018) — 1,986 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- AutoAugment: Learning Augmentation Strategies From Data (2019) — 2,652 citations
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020) — 4,872 citations
- Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (2020) — 1,320 citations
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (2019) — 4,125 citations
- Revisiting ResNets: Improved Training and Scaling Strategies (2021) — 365 citations
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty (2019) — 1,617 citations
- RandAugment: Practical data augmentation with no separate search (2019) — 265 citations
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring (2019) — 796 citations
- A Fourier Perspective on Model Robustness in Computer Vision (2019) — 638 citations
- Learning Data Augmentation Strategies for Object Detection (2019) — 607 citations
- ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring (2020) — 479 citations
- Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation (2019) — 229 citations
- Adversarial Examples Are a Natural Consequence of Test Error in Noise (2019) — 343 citations
- Intriguing Properties of Adversarial Examples (2017) — 90 citations
- Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation (2020) — 121 citations
- No One Representation to Rule Them All: Overlapping Features of Training Methods (2021) — 72 citations
- Affinity and Diversity: Quantifying Mechanisms of Data Augmentation (2020) — 87 citations