[1409.4842] Going Deeper with Convolutionsopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

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 (ILSVRC 2014). 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 ILSVRC 2014 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

1 mentions: @allowfirm
Date: 2020/09/14 12:52

Referring Tweets

@allowfirm GoogLeNet(初代Inception)の論文( t.co/quizUIMKe1 )で「Inception」の由来は、同名の映画のミーム「We Need To Go Deeper」( t.co/z6241PQfnm )からと論文で明記していたことに、Andrew NgさんのCoursera動画( t.co/jKmsBiIIir )で気付きました。

Bookmark Comments

Related Entries

Read more [サーベイ論文] Deep Learningを用いた歩行者検出の研究動向
4 users, 0 mentions 2019/03/13 09:47
Read more GitHub - wuhuikai/FastFCN: FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segm...
2 users, 0 mentions 2019/04/03 08:17
Read more Deep Forest: Towards An Alternative to Deep Neural Networks
2 users, 0 mentions 2019/08/19 08:16
Read more [1808.02590] A Tutorial on Network Embeddings
3 users, 0 mentions 2019/10/04 00:49
Read more Kaggle_the 2nd youtube-8m video understanding challenge
3 users, 0 mentions 2020/01/08 06:51