Sotabase

Career

· Founder And CEO, Centropy, Inc.2024–2024
· Co-Founder, Stealth startup (Current)2024–
· Staff Research Scientist, Meta2022–2024
· Senior Research Scientist, Meta2021–2022
· Research Scientist, Meta2020–2021
· Software Engineer Intern, Google2016–2016
· Software Engineering Intern, Analog Devices2014–2014
· Doctor of Philosophy - PhD EECS, University of California, Berkeley2013–2019

Publications (60)

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Computer Vision and Pattern Recognition · 2018
1,394
cited
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
IEEE International Conference on Robotics and Automation · 2017
889
cited
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
IEEE International Conference on Robotics and Automation · 2018
688
cited
Visual Transformers: Token-based Image Representation and Processing for Computer Vision
arXiv.org · 2020
680
cited
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
Computer Vision and Pattern Recognition · 2022
628
cited
Unbiased Teacher for Semi-Supervised Object Detection
International Conference on Learning Representations · 2021
572
cited
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2016
530
cited
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
European Conference on Computer Vision · 2020
412
cited
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
390
cited
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Computer Vision and Pattern Recognition · 2020
321
cited
SqueezeNext: Hardware-Aware Neural Network Design
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2018
320
cited
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
IEEE Transactions on Neural Networks and Learning Systems · 2020
316
cited
Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
arXiv.org · 2018
297
cited
ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation
Computer Vision and Pattern Recognition · 2018
284
cited
Cross-Domain Adaptive Teacher for Object Detection
Computer Vision and Pattern Recognition · 2021
256
cited
A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving
International Conference on Multimedia Retrieval · 2018
232
cited
Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs
Symposium on Field Programmable Gate Arrays · 2018
122
cited
ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation
AAAI Conference on Artificial Intelligence · 2020
108
cited
FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining
Computer Vision and Pattern Recognition · 2021
105
cited
FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function
arXiv.org · 2020
75
cited
Sotabase
Bichen Wu | Researcher Profile | Sotabase | Sotabase