ResNet (二):Overview
2020/12/23
-----
https://pixabay.com/zh/photos/sisters-summer-child-girls-931151/
-----
◎ Abstract
-----
◎ Introduction
-----
本論文要解決(它之前研究)的(哪些)問題(弱點)?
-----
# VGGNet。
說明:
沒有恆等映射的網路。
-----
Figure 3: GoogLeNet network with all the bells and whistles.
# GoogLeNet
說明:
有恆等映射的代替物(輔助的輸出層)。某方面,可以說 ResNet 是 VGGNet 與 GoogLeNet 的整合。
-----
◎ Method
-----
解決方法?
-----
# ResNet v1。
說明:
加上恆等映射後,只要訓練殘差。
-----
# ResNet v2。
說明:
更完整的恆等映射。
-----
具體細節?
https://hemingwang.blogspot.com/2021/03/resnetillustrated.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。
-----
方法比較。
-----
◎ Conclusion
-----
◎ Future Work
-----
後續相關領域的研究。
-----
Figure 1: Schematics of network architectures.
# NDENet
說明:
https://www.jiqizhixin.com/articles/2019-05-17-7
-----
Table 1: In this table, we list a few popular deep networks, their associated ODEs and the numerical schemes that are connected to the architecture of the networks.
表1:在此表中,我們列出了一些流行的深度網路,與之關聯的 ODE 以及與網路架構連接的數值方案。
# NDENet
說明:
https://www.jiqizhixin.com/articles/2019-05-17-7
-----
後續延伸領域的研究。
-----
# Transformer。
說明:
Transformer 有使用恆等映射。
-----
◎ References
-----
# VGGNet。被引用 47721 次。以兩個 conv3 組成一個 conv5,反覆加深網路至 16 與 19 層。
Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
https://arxiv.org/pdf/1409.1556.pdf
# GoogLeNet
Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
# ResNet v1。被引用 61600 次。加上靈感來自 LSTM 的 identity mapping,網路可到百層。
He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
https://openaccess.thecvf.com/content_cvpr_2016/papers/He_Deep_Residual_Learning_CVPR_2016_paper.pdf
# ResNet v2。被引用 4560 次。重點從 residual block 轉移到 pure identity mapping,網路可到千層。
He, Kaiming, et al. "Identity mappings in deep residual networks." European conference on computer vision. Springer, Cham, 2016.
https://arxiv.org/pdf/1603.05027.pdf
# NDENet
Lu, Yiping, et al. "Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations." International Conference on Machine Learning. PMLR, 2018.
https://arxiv.org/pdf/1710.10121.pdf
http://proceedings.mlr.press/v80/lu18d/lu18d.pdf
# Transformer
Vaswani, Ashish, et al. "Attention is all you need." Advances in Neural Information Processing Systems. 2017.
https://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf
-----
No comments:
Post a Comment