刚刚有个同学问我:“深层神经网络如果去掉一部分残差,到底还能不能正常训练呀?”这个问题着实很好,我也没思考过,也没尝试过,然后试着去Google Scholar检索了一下关键词“without shorcut”,于是看到了以下的文章。让我比较惊奇的是,这是个很多人研究的方向,并且近年来不少文章发表在AI三大会。其中包含:1)残差的融合提高效率(重参数化);2)去除一部分残差提高效率;3)用更好的架构替代传统残差等多个方面,还挺值得总结一下的。文章来源地址https://www.toymoban.com/news/detail-552972.html
- [CVPR 2023] Localized Shortcut Removal [paper]
- [ICLR 2023] Deep transformers without shortcuts: Modifying self-attention for faithful signal propagation [paper]
- [ICLR 2022] Deep learning without shortcuts: Shaping the kernel with tailored rectifiers [paper]
- [NeurIPS 2022] Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers [paper]
- [ICML 2022] Monitoring Shortcut Learning using Mutual Information [paper]
- [CVPR 2021] RepVGG: Making VGG-style ConvNets Great Again [paper]
- 注:Xiaohan Ding的结构重参数化系列都有残差分支和卷积分支的融合
- [ICML 2020] Automatic Shortcut Removal for Self-Supervised Representation Learning [paper]
- [NeurIPS 2020] Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts [paper]
- [arXiv 2019] RMNet: Equivalently Removing Residual Connection from Networks [paper]
- [arXiv 2017] DiracNets: Training Very Deep Neural Networks Without Skip-Connections [paper]
- 注:非常早期的一篇经典论文,将残差融合进权重
文章来源:https://www.toymoban.com/news/detail-552972.html
到了这里,关于【深度学习随笔】神经网络中去掉残差连接的工作的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!