GoogleNet算法的简介
GoogleNet，来自Google公司研究员。以GoogleNet(Inception v1)为例，于2014年ILSVRC竞赛图像分类任务第一名(6.67% top-5 error)。GoogLeNet设计了22层卷积神经网络，依然是没有最深，只有更深，性能与VGGNet相近。
Abstract
We propose a deep convolutional neural network architecture codenamed Inception, which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
摘要
我们提出了一种深卷积神经网络结构，代号为“Inception”，负责在ImageNet大规模视觉识别挑战2014 (ILSVRC14)中设置分类和检测的最新技术。这种体系结构的主要特点是提高了网络内计算资源的利用率。这是通过精心设计的设计实现的，该设计允许在保持计算预算不变的同时增加网络的深度和宽度。为了优化质量，架构决策基于Hebbian原理和多尺度处理的直觉。在我们提交的ILSVRC14中使用的一种特殊形式是GoogLeNet，它是一个22层的深层网络，其质量是在分类和检测的背景下评估的。
Conclusions
Our results seem to yield a solid evidence that approximating the expected optimal sparse structure by readily available dense building blocks is a viable method for improving neural networks for computer vision. The main advantage of this method is a significant quality gain at a modest increase of computational requirements compared to shallower and less wide networks. Also note that our detection work was competitive despite of neither utilizing context nor performing bounding box regression and this fact provides further evidence of the strength of the Inception architecture. Although it is expected that similar quality of result can be achieved by much more expensive networks of similar depth and width, our approach yields solid evidence that moving to sparser architectures is feasible and useful idea in general. This suggest promising future work towards creating sparser and more refined structures in automated ways on the basis of [2].
结论
我们的结果似乎提供了一个坚实的证据，逼近预期的最优稀疏结构，由现成的密集building blocks是一个可行的方法，以改善神经网络的计算机视觉。这种方法的主要优点是，与较浅且较宽的网络相比，在计算量适度增加的情况下，可以显著提高质量。还要注意，我们的检测工作是竞争性的，尽管既没有使用上下文，也没有执行边界框回归，这一事实为Inception架构的强度提供了进一步的证据。虽然期望通过更昂贵的深度和宽度相似的网络可以获得类似质量的结果，但我们的方法提供了坚实的证据，表明转向更稀疏的体系结构通常是可行和有用的。这表明未来有希望在[2]的基础上以自动化的方式创建更稀疏和更精细的结构。
1、实验结果
论文
Christian Szegedy et al（2015）: Going Deeper With Convolutions. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Christian Szegedy, Wei Liu, YangqingJia, Pierre Sermanet, Scott Reed, et al.
Going Deeper with Convolutions. CVPR, 2015
https://arxiv.org/abs/1409.4842
