Sunday, April 25, 2021

GoogLeNet(二):Overview

GoogLeNet(二):Overview

2020/12/28

-----


https://pixabay.com/zh/photos/mac-freelancer-macintosh-macbook-459196/

-----

◎ Abstract

-----

◎ Introduction

-----

本論文要解決(它之前研究)的(哪些)問題(弱點)? 

-----


# NIN。

-----


# Provable bounds

Arora 等 [2] 提出了一種逐層構造的方法:分析最後一層的相關性統計數據並將它們聚類為具有高度相關性的單元組。 這些群集形成下一層的單元,並連接到上一層的單元。(摘自論文)。

-----

◎ Method

-----

解決方法? 

-----


# GoogLeNet。

-----

具體細節?

http://hemingwang.blogspot.com/2021/03/googlenetillustrated.html

-----

◎ Result

-----

本論文成果。 

-----

◎ Discussion

-----

本論文與其他論文(成果或方法)的比較。 

-----

成果比較。 

-----


# GoogLeNet

-----

方法比較。 

-----

◎ Conclusion 

-----

◎ Future Work

-----

後續相關領域的研究。 

-----


Figure 1: A 5-layer dense block with a growth rate of k = 4. Each layer takes all preceding feature-maps as input.

圖1:一個 5 層密集塊,增長率為 k = 4。每一層都將所有先前的特徵圖作為輸入。

# DenseNet

-----

後續延伸領域的研究。

-----


Figure 4. An “extreme” version of our Inception module, with one spatial convolution per output channel of the 1x1 convolution.

圖4. 我們的 Inception 模塊的“極端”版本,每個 1x1 卷積的輸出通道都有一個空間卷積。

# Xception

-----

-----

◎ References

-----

# NIN。被引用 4475 次。Channel(feature maps) 之間的 fusion。可用於升維或降維(改變特徵圖的數目)。

Lin, Min, Qiang Chen, and Shuicheng Yan. "Network in network." arXiv preprint arXiv:1312.4400 (2013).

https://arxiv.org/pdf/1312.4400.pdf


# Provable bounds

Arora, Sanjeev, et al. "Provable bounds for learning some deep representations." International conference on machine learning. PMLR, 2014.

http://proceedings.mlr.press/v32/arora14.pdf


# GoogLeNet。被引用 25849 次。成功將 NIN 的一維卷積運用於大型網路,效能略優於 VGGNet。

Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.

https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Szegedy_Going_Deeper_With_2015_CVPR_paper.pdf


# DenseNet

Huang, Gao, et al. "Densely connected convolutional networks." Proceedings of the IEEE conference on computer vision and pattern recognition. Vol. 1. No. 2. 2017.

http://openaccess.thecvf.com/content_cvpr_2017/papers/Huang_Densely_Connected_Convolutional_CVPR_2017_paper.pdf


# Xception

Chollet, François. "Xception: Deep learning with depthwise separable convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.

https://openaccess.thecvf.com/content_cvpr_2017/papers/Chollet_Xception_Deep_Learning_CVPR_2017_paper.pdf

-----

No comments:

Post a Comment

Note: Only a member of this blog may post a comment.