SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

Alvin Wan, Xiangyu Yue, Kurt Keutzer

Lidar SimulatorConvolutional Neural NetworkEngineeringMachine LearningPoint Cloud Processing +16

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

Alvin Wan, Forrest Iandola, Peter H. Jin, +1

Convolutional Neural NetworkImage AnalysisMachine VisionMachine LearningEngineering +13

Visual Transformers: Token-based Image Representation and Processing for Computer Vision

Chenfeng Xu, Xiaoliang Dai, Alvin Wan, +1

arXiv (Cornell University)

Semantic Token SpaceConvolutional Neural NetworkEngineeringFeature DetectionMachine Learning +16

Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions

Alvin Wan, Xiangyu Yue, Peter Jin, +5

Convolutional Neural NetworkEngineeringMachine LearningZero FlopImage Analysis +20

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Alvin Wan, Xiaoliang Dai, Peizhao Zhang, +8

Geometric LearningEngineeringMachine LearningComputer ArchitectureEfficient Dnas Variant +17

Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning

Vladimir Feinberg, Alvin Wan, Ion Stoica, +3

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningDynamics ModelIntelligent Systems +14

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

Alvin Wan, Forrest Iandola, Peter Jin, +1

arXiv (Cornell University)

Convolutional Neural NetworkImage AnalysisMachine LearningMachine VisionEngineering +13

FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining

Xiaoliang Dai, Alvin Wan, Peizhao Zhang, +7

Artificial IntelligenceStructured PredictionModel OptimizationEnlarged Search SpaceEngineering +13

Visual Transformers: Where Do Transformers Really Belong in Vision Models?

Chenfeng Xu, Xiaoliang Dai, Alvin Wan, +6

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Convolutional Neural NetworkEngineeringMachine LearningNeural NetworkLow-level Vision +14

NBDT: Neural-Backed Decision Trees

Alvin Wan, Lisa Dunlap, Daniel E. Ho, +6

arXiv (Cornell University)

Artificial IntelligenceSurrogate LossEngineeringMachine LearningNeural Networks (Machine Learning) +19