Kurt Keutzer
Artificial Intelligence · 2000–2025
A researcher in the Science corpus: 66 papers; trusts 3,514 researchers and is trusted by 2,759 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,727 citations into it; #1,768 of 36,961 by trust here, #667 by citations
- Computer Vision and Pattern Recognition — 1,577 citations into it; #1,011 of 21,973 by trust here, #532 by citations
- Efficiency & Compression — 515 citations into it; #64 of 1,273 by trust here, #16 by citations
- Model Architectures — 341 citations into it; #1,578 of 2,288 by trust here, #547 by citations
- Optimization & Training — 321 citations into it; #1,055 of 2,605 by trust here, #320 by citations
- Large Language Models — 221 citations into it
- Natural Language Processing — 215 citations into it
- Evaluation & Benchmarks — 177 citations into it; #2,492 of 3,155 by trust here, #2,140 by citations
Whom Kurt Keutzer trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Yann LeCun
- Ilya Sutskever
- Ross B. Girshick
- Christian Szegedy
- Karen Simonyan
Who trusts Kurt Keutzer overall
- Zi-Mei Yao
- A. Gholami
- Bichen Wu
- Matthias Gries
- Sehoon Kim
- Zhen Dong
- Yang You
- Sergey I. Nikolenko
- Sheng Shen
- Michael W. Mahoney
Papers from Kurt Keutzer's perspective
Ordered by how strongly the researchers Kurt Keutzer trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size (2016) — 8,474 citations
- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search (2018) — 1,467 citations
- Large Batch Optimization for Deep Learning: Training BERT in 76 minutes (2019) — 1,222 citations
- Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow (2010) — 526 citations
- How Much Can CLIP Benefit Vision-and-Language Tasks? (2021) — 516 citations
- Visual Transformers: Token-based Image Representation and Processing for Computer Vision (2020) — 755 citations
- ImageNet Training in Minutes (2017) — 470 citations
- Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions (2017) — 401 citations
- Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT (2019) — 675 citations
- Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers (2020) — 157 citations
- FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters (2015) — 312 citations
- Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization (2019) — 244 citations
- Hessian-based Analysis of Large Batch Training and Robustness to Adversaries (2018) — 194 citations
- Efficient, high-quality image contour detection (2009) — 143 citations
- SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud (2017) — 932 citations
- - LEVEL ACCURACY WITH 50 X FEWER PARAMETERS AND < 0 . 5 MB MODEL SIZE (2016)
- ZeroQ: A Novel Zero Shot Quantization Framework (2020) — 496 citations
- PyHessian: Neural Networks Through the Lens of the Hessian (2019) — 401 citations
- Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers (2020) — 187 citations
- Fast support vector machine training and classification on graphics processors (2008) — 415 citations