DeepAI AI Chat
Log In Sign Up

Rethinking the Inception Architecture for Computer Vision

12/02/2015
by   Christian Szegedy, et al.
Google
0

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios. Here we explore ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. We benchmark our methods on the ILSVRC 2012 classification challenge validation set demonstrate substantial gains over the state of the art: 21.2 top-5 error for single frame evaluation using a network with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. With an ensemble of 4 models and multi-crop evaluation, we report 3.5 17.3

READ FULL TEXT

page 1

page 2

page 3

page 4

11/03/2020

Similarity-Based Clustering for Enhancing Image Classification Architectures

Convolutional networks are at the center of best in class computer visio...
04/04/2019

Video Classification with Channel-Separated Convolutional Networks

Group convolution has been shown to offer great computational savings in...
06/06/2016

Very Deep Convolutional Networks for Text Classification

The dominant approach for many NLP tasks are recurrent neural networks, ...
11/17/2016

PolyNet: A Pursuit of Structural Diversity in Very Deep Networks

A number of studies have shown that increasing the depth or width of con...
12/15/2017

Learning when to skim and when to read

Many recent advances in deep learning for natural language processing ha...
09/05/2019

Multi-layer Domain Adaptation for Deep Convolutional Networks

Despite their success in many computer vision tasks, convolutional netwo...
12/20/2013

Fast Training of Convolutional Networks through FFTs

Convolutional networks are one of the most widely employed architectures...

Code Repositories

deepmark

THE Deep Learning Benchmarks


view repo

terngrad

Ternary Gradients to Reduce Communication in Distributed Deep Learning (TensorFlow)


view repo

Inception_v3_GoogLeNet

GoogleNet Inception v3


view repo

Perfect-TensorFlow-Demo-Vision

Perfect TensorFlow Server Example of Computer Vision


view repo

googlenet

Implementation of GoogLeNet by chainer (Going Deeper with Convolutions: https://arxiv.org/abs/1409.4842)


view repo