Identity Mappings in Deep Residual Networks

Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

ECCV 2016 pp. 630-645

doi:10.1007/978-3-319-46493-0_38 /eccv/2016/he2016eccv-identity/

Abstract

Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. A series of ablation experiments support the importance of these identity mappings. This motivates us to propose a new residual unit, which makes training easier and improves generalization. We report improved results using a 1001-layer ResNet on CIFAR-10 (4.62 % error) and CIFAR-100, and a 200-layer ResNet on ImageNet. Code is available at: https://github.com/KaimingHe/resnet-1k-layers.

PDF ECCV Semantic Scholar

Cite

Text

He et al. "Identity Mappings in Deep Residual Networks." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46493-0_38

Markdown

[He et al. "Identity Mappings in Deep Residual Networks." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/he2016eccv-identity/) doi:10.1007/978-3-319-46493-0_38

BibTeX

@inproceedings{he2016eccv-identity,
  title     = {{Identity Mappings in Deep Residual Networks}},
  author    = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle = {European Conference on Computer Vision},
  year      = {2016},
  pages     = {630-645},
  doi       = {10.1007/978-3-319-46493-0_38},
  url       = {https://mlanthology.org/eccv/2016/he2016eccv-identity/}
}