Light-weight neural networks
 
Edit

Computer Vision • 21 methods

Lightweight neural networks or mobile-friendly neural networks are deep neural networks which are designed for mobile devices or other resource-limited hardwares

Methods
Add a Method

Method Year Papers
MobileNetV2
MobileNetV2: Inverted Residuals and Linear Bottlenecks
2018 387
SqueezeNet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
2016 94
MobileNetV3
Searching for MobileNetV3
2019 89
MobileNetV1
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
2017 74
ShuffleNet
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
2017 50
GhostNet
GhostNet: More Features from Cheap Operations
2019 22
ESPNet
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
2018 22
MobileViT
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
2021 21
MnasNet
MnasNet: Platform-Aware Neural Architecture Search for Mobile
2018 20
FBNet
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
2018 12
MixNet
MixConv: Mixed Depthwise Convolutional Kernels
2019 12
MobileViTv2
Separable Self-attention for Mobile Vision Transformers
2022 5
PeleeNet
Pelee: A Real-Time Object Detection System on Mobile Devices
2018 3
MoViNet
MoViNets: Mobile Video Networks for Efficient Video Recognition
2021 2
MobileDet
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
2020 2
ProxylessNet-Mobile
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
2018 2
MoGA-A
MoGA: Searching Beyond MobileNetV3
2019 1
MoGA-B
MoGA: Searching Beyond MobileNetV3
2019 1
MoGA-C
MoGA: Searching Beyond MobileNetV3
2019 1
ESPNetv2
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
2018 1
MobileViTv3
MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features
2022 1
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy