AIConfPaper
← Search

Matthew Yu

3 accepted papers

2023

A Practical Stereo Depth System for Smart Glasses

Jialiang Wang, Daniel Scharstein, Akash Bapat, Kevin Blackburn-Matzen, Matthew Yu, Jonathan Lehman +8
CVPR 2023poster

We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with a fallback to monocular depth estimation when rectification is unreliable. The output of our depth sensing system is then used in a…

Cited by 7Source ↗PDF ↗Scholar ↗
2021

FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining

Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Bichen Wu, Zijian He, Zhen Wei +5
CVPR 2021poster

Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts. However, previous NAS methods search for architectures under one set of training hyper-parameters (i.e., a training recipe), overlooking superior architecture-recipe co…

Cited by 133PDF ↗Scholar ↗
2020

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie +6
CVPR 2020poster

Differentiable Neural Architecture Search (DNAS) has demonstrated great success in designing state-of-the-art, efficient neural networks. However, DARTS-based DNAS's search space is small when compared to other search methods', since all candidate network layers must be explicitly instantiated in me…

Cited by 383PDF ↗code ↗Scholar ↗