Yefei He
University of Iowa
12 Papers
85 Citations
Yefei He is an academic researcher from University of Iowa. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 3, co-authored 4 publications.
Chat about Author
Papers
DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
Wei Wu,Yuzhong Zhao,Hao Chen,Yu-Chao Gu,Rui-Wei Zhao,Yefei He,Hong Zhou,Mike Zheng Shou,Chunhua Shen +8 more
TL;DR: This paper builds upon the pre-trained diffusion model and extends text-guided image synthesis to perception data generation, and shows that the rich latent code of the diffusion model can be effectively decoded as accurate perception annotations using a decoder module.
Updates to Research on Recommended Minimum Levels for Pavement Marking Retroreflectivity to Meet Driver Night Visibility Needs
Chris Debaillon,Paul J Carlson,Yefei He,Thomas Schnell,Fuat Aktan +4 more
- 01 Oct 2007
TL;DR: In this paper, a comprehensive survey on the factors that affect pavement marking visibility and minimum RL levels was performed, with key factors identified, including pavement marking configuration, pavement surface type, vehicle speed, vehicle type, and presence of RRPMs.
51
PTQD: Accurate Post-Training Quantization for Diffusion Models
TL;DR: In this paper , a unified formulation for quantization noise and diffusion perturbed noise in the quantized denoising process is proposed, which can significantly reduce the model size and accelerate the sampling process without requiring any re-training.
Review and Development of Recommended Minimum Pavement Marking Retroreflectivity Levels
TL;DR: A previous study performed in the 1990s using a computer model called the Computer-Aided Road-Marking Visibility Evaluator resulted in a table of minimum levels of pavement marking retroreflectivity values that FHWA used to develop its initial set of minimum pavement marking reflective levels.
25
Is More Better? — Night Vision Enhancement System’s Pedestrian Warning Modes and Older Drivers
Tim Brown,Yefei He,Cheryl A. Roe,Thomas Schnell +3 more
- 01 Jan 2010
TL;DR: Examination of performance differences of a NVES with six different configurations of warning cues demonstrated that multi-modal warnings involving visual cues degraded the effectiveness of NVES for older drivers.
13