B
Bichen Wu
Researcher at Facebook
Publications - 72
Citations - 6142
Bichen Wu is an academic researcher from Facebook. The author has contributed to research in topics: Artificial neural network & Object detection. The author has an hindex of 23, co-authored 66 publications receiving 3476 citations. Previous affiliations of Bichen Wu include University of California, Berkeley.
Papers
More filters
Proceedings ArticleDOI
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Bichen Wu,Kurt Keutzer,Xiaoliang Dai,Peizhao Zhang,Yanghan Wang,Fei Sun,Yiming Wu,Yuandong Tian,Peter Vajda,Yangqing Jia +9 more
TL;DR: This work proposes a differentiable neural architecture search (DNAS) framework that uses gradient-based methods to optimize ConvNet architectures, avoiding enumerating and training individual architectures separately as in previous methods.
Proceedings ArticleDOI
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
TL;DR: Wu et al. as mentioned in this paper proposed an end-to-end pipeline called SqueezeSeg based on convolutional neural networks (CNN) for semantic segmentation of road-objects from 3D LiDAR point clouds.
Proceedings ArticleDOI
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
TL;DR: SqueezeDet is a fully convolutional neural network for object detection that aims to simultaneously satisfy all of the above constraints, and is very accurate, achieving state-of-the-art accuracy on the KITTI benchmark.
Proceedings ArticleDOI
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
TL;DR: Zhou et al. as mentioned in this paper proposed a new model SqueezeSegV2, which is more robust against dropout noises in LiDAR point cloud and therefore achieves significant accuracy improvement.
Proceedings ArticleDOI
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
Bichen Wu,Alvin Wan,Xiangyu Yue,Peter H. Jin,Sicheng Zhao,Noah Golmant,Amir Gholaminejad,Joseph E. Gonzalez,Kurt Keutzer +8 more
TL;DR: ShiftNet as discussed by the authors replaces expensive spatial convolutions with shift-based modules for image classification, face verification, and style transfer, achieving state-of-the-art performance on ImageNet.