571 citations · 662 across the 6 of their papers we have counts for
6 papers
MoST: Multi-modality Scene Tokenization for Motion Prediction
Norman Mu, Jingwei Ji, Zhenpei Yang +11
Many existing motion prediction approaches rely on symbolic perception outputs to generate agent trajectories, such as bounding boxes, road graph information and traffic lights. Th…
SLIP: Self-supervision meets Language-Image Pre-training
Norman Mu, Alexander Kirillov, David Wagner +1
Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. CLIP, an exciting new approach to le…
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
Dan Hendrycks, Steven Basart, Norman Mu +10
We introduce four new real-world distribution shift datasets consisting of changes in image style, image blurriness, geographic location, camera operation, and more. With our new d…
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Dan Hendrycks, Norman Mu, Ekin D. Cubuk +3
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated i…
MNIST-C: A Robustness Benchmark for Computer Vision
Norman Mu, Justin Gilmer
We introduce the MNIST-C dataset, a comprehensive suite of 15 corruptions applied to the MNIST test set, for benchmarking out-of-distribution robustness in computer vision. Through…
Parameter Re-Initialization through Cyclical Batch Size Schedules
Norman Mu, Zhewei Yao, Amir Gholami +2
Optimal parameter initialization remains a crucial problem for neural network training. A poor weight initialization may take longer to train and/or converge to sub-optimal solutio…