Deep Residual Learning for Image Recognition

@article{He2015DeepRL,
  title={Deep Residual Learning for Image Recognition},
  author={Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={770-778}
}
Highlight Information
Deeper neural networks are more difficult to train. [...] Key Method We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers - 8× deeper than VGG nets [40] but still having lower…Expand Abstract

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 29,768 CITATIONS

Intra-clip Aggregation for Video Person Re-identification

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Re-ID done right: towards good practices for person re-identification

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Towards Image Understanding from Deep Compression without Decoding

VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning

VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Novel Method for Person Re-Identification: Conditional Translated Network Based on GANs

VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A revisit to MacKay algorithm and its application to deep network compression

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers' Outputs

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2005
2020

CITATION STATISTICS

  • 7,976 Highly Influenced Citations

  • Averaged 9,100 Citations per year from 2017 through 2019

  • 43% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 50 REFERENCES

Microsoft COCO: Common Objects in Context

VIEW 15 EXCERPTS
HIGHLY INFLUENTIAL

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

VIEW 9 EXCERPTS

Highway Networks

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

VIEW 5 EXCERPTS

FitNets: Hints for Thin Deep Nets

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Fast R-CNN

  • Ross B. Girshick
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
VIEW 1 EXCERPT

Fully convolutional networks for semantic segmentation

VIEW 1 EXCERPT