6.5k citations · 10.4k across the 118 of their papers we have counts for
5 papers · 1 filter
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
Bichen Wu, Alvin Wan, Xiangyu Yue +6
Neural networks rely on convolutions to aggregate spatial information. However, spatial convolutions are expensive in terms of model size and computation, both of which grow quadra…
Integrated Model, Batch and Domain Parallelism in Training Neural Networks
Amir Gholami, Ariful Azad, Peter Jin +2
We propose a new integrated method of exploiting model, batch and domain parallelism for the training of deep neural networks (DNNs) on large distributed-memory computers using min…
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
Bichen Wu, Alvin Wan, Xiangyu Yue +1
In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds. In particular, we wish to detect and categorize instances of interest, such as cars, ped…
Keynote: Small Neural Nets Are Beautiful: Enabling Embedded Systems with Small Deep-Neural-Network Architectures
Forrest Iandola, Kurt Keutzer
Over the last five years Deep Neural Nets have offered more accurate solutions to many problems in speech recognition, and computer vision, and these solutions have surpassed a thr…
Regret Minimization for Partially Observable Deep Reinforcement Learning
Peter Jin, Kurt Keutzer, Sergey Levine
Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning…