MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (2017-04-17T00:00:00.000000Z)

TL;DR

This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.

Abstract

We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.

Authors

Dmitry Kalenichenko

4 papers

Andrew G. Howard

7 papers

Hartwig Adam

15 papers

TL;DR

Abstract

Authors

References38 items

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

Xception: Deep Learning with Depthwise Separable Convolutions

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

Factorized Convolutional Neural Networks

Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial "Bottleneck" Structure

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

PlaNet - Photo Geolocation with Convolutional Neural Networks

Quantized Convolutional Neural Networks for Mobile Devices

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

Rethinking the Inception Architecture for Computer Vision

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition

Structured Transforms for Small-Footprint Deep Learning

Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Compressing Neural Networks with the Hashing Trick

FaceNet: A unified embedding for face recognition and clustering

Distilling the Knowledge in a Neural Network

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Deep Fried Convnets

Training deep neural networks with low precision multiplications

Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition

Flattened Convolutional Neural Networks for Feedforward Acceleration

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

Caffe: Convolutional Architecture for Fast Feature Embedding

Speeding up Convolutional Neural Networks with Low Rank Expansions

ImageNet classification with deep convolutional neural networks

IM2GPS: estimating geographic information from a single image

Yfcc100m: The new data in multimedia research

Large-Scale Image Geolocalization

Tensorflow: Large-scale machine learning on heterogeneous systems

Rigid-motion scattering for image classification

Novel Dataset for Fine-Grained Image Categorization : Stanford Dogs

Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names