Rethinking the Inception Architecture for Computer Vision

https://arxiv.org/abs/1512.00567

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-1 and 5.6% 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% top-5 error on the validation set (3.6% error on the test set) and 17.3% top-1 error on the validation set.

时间: 2024-10-31 11:31:51

Rethinking the Inception Architecture for Computer Vision的相关文章

Rethinking the inception architecture for computer vision的 paper 相关知识

这一篇论文很不错,也很有价值;它重新思考了googLeNet的网络结构--Inception architecture,在此基础上提出了新的改进方法; 文章的一个主导目的就是:充分有效地利用computation; 第一部分: 文章提出了四个principles: 原则1:设计网络的时候需要避免 representational bottlenecks; 什么意思呢? 文章中说: 层与层之间进行 information 传递时,要避免这个过程中的数据的extreme compression,也就

【Network architecture】Rethinking the Inception Architecture for Computer Vision(inception-v3)论文解析

0. paper link inception-v3 1. Overview ??这篇文章很多"经验"性的东西,因此会写的比较细,把文章里的一些话摘取出来,多学习一下,希望对以后自己设计网络有帮助. 2. Four General Design Principles ??这里文章介绍了四种设计网络设计原则,这是作者利用各种卷积网络结构,通过大量的实验推测的. 避免特征表示瓶颈,尤其是在网络的前面.要避免严重压缩导致(pooling,卷积等操作)的瓶颈.特征表示尺寸应该温和的减少,从输入

Analyzing The Papers Behind Facebook's Computer Vision Approach

Analyzing The Papers Behind Facebook's Computer Vision Approach Introduction You know that company called Facebook? Yeah, the one that has 1.6 billion people hooked on their website. Take all of the happy birthday posts, embarrassing pictures of you

计算机视觉和人工智能的状态:我们已经走得很远了 The state of Computer Vision and AI: we are really, really far away.

The picture above is funny. But for me it is also one of those examples that make me sad about the outlook for AI and for Computer Vision. What would it take for a computer to understand this image as you or I do? I challenge you to think explicitly

My Reading List - Machine Learning && Computer Vision

本博客汇总了个人在学习过程中所看过的一些论文.代码.资料以及常用的资源与网站,为了便于记录自身的学习过程,将其整理于博客之中. Machine Learning (1) Machine Learning Video Library - Caltech说明:罗列了机器学习的常用算法以及机器学习图谱 (2) Deep Learning - Bengio 说明:Deep Learning三大牛之一Bengio写的一本书 (3) Understanding LSTM Networks 说明:非常棒的LS

Graph Cut and Its Application in Computer Vision

Graph Cut and Its Application in Computer Vision 原文出处: http://lincccc.blogspot.tw/2011/04/graph-cut-and-its-application-in.html 网络流算法最初用于解决流网络的优化问题,比如水管网络.通信传输和城市的车流等.Graph cut作为其中一类最常见的算法,用于求解流网络的最小割,即寻找一个总容量最小的边集合,去掉这个集合中的所有边将阻断这个网络.图像和视频也能被视作网络(或者

Computer Vision的尴尬---by林达华

Computer Vision的尴尬---by林达华 Computer Vision是AI的一个非常活跃的领域,每年大会小会不断,发表的文章数以千计(单是CVPR每年就录取300多,各种二流会议每年的文章更可谓不计其数),新模型新算法新应用层出不穷.可是,浮华背后,根基何在?对于Vision,虽无大成,但涉猎数年,也有管窥之见.Vision所探索的是一个非常复杂的世界,对于这样的世界如何建模,如何分析,却一直没有受普遍承认的理论体系.大部分的研究工作,循守着几种模式:o    从上游学科(比如立

[新书推荐]A Practical Introduction to Computer Vision with OpenCV

一本opencv好书,  在我上传的资源里 http://download.csdn.net/detail/qq_21970857/8504829 Computer Vision is a rapidly expanding area and it is becomingprogressively easier for developers to make use of this field dueto the ready availability of high quality librari

Computer Vision: OpenCV, Feature Tracking, and Beyond--From <<Make Things See>> by Greg

In the 1960s, the legendary Stanford artificial intelligence pioneer, John McCarthy, famously gave a graduate student the job of “solving” computer vision as a summer project. It has occupied an entire community of academic researchers for the past 4