Ross Wightman
Computer Vision and Pattern Recognition · 2021–2022
A researcher in the Science corpus: 4 papers; trusts 562 researchers and is trusted by 49 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 200 citations into it; #4,237 of 21,575 by trust here, #2,332 by citations
- Artificial Intelligence — 160 citations into it; #7,646 of 35,345 by trust here, #3,080 by citations
- Evaluation & Benchmarks — 47 citations into it
- Representation & Self-Supervised Learning — 40 citations into it
- Model Architectures — 31 citations into it; #751 of 2,278 by trust here, #1,475 by citations
- Optimization & Training — 30 citations into it; #1,029 of 2,601 by trust here, #1,468 by citations
- Efficiency & Compression — 12 citations into it
- Safety, Robustness & Interpretability — 12 citations into it
Whom Ross Wightman trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Ilya Sutskever
- Christian Szegedy
- Ross B. Girshick
- Yoshua Bengio
- Diederik P. Kingma
- Quoc V. Le
- Yann LeCun
Who trusts Ross Wightman overall
- Xiaohua Zhai
- Sachin Mehta
- Jianwei Yang
- Zhiqiang Shen
- Asher Trockman
- Weihao Yu
- Hugo Touvron
- Zizheng Pan
- Shoufa Chen
- Ali Hassani
Papers from Ross Wightman's perspective
Ordered by how strongly the researchers Ross Wightman 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)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Going deeper with convolutions
Their papers
- LAION-5B: An open large-scale dataset for training next generation image-text models (2022) — 5,389 citations
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers (2021) — 854 citations
- Reproducible Scaling Laws for Contrastive Language-Image Learning (2022) — 1,494 citations
- ResNet strikes back: An improved training procedure in timm (2021) — 625 citations