Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
Summary
The authors introduced a residual learning framework that reformulates network layers to learn residual functions with reference to their inputs (via identity 'shortcut' connections), making very deep networks substantially easier to optimize. They showed that such residual networks gain accuracy from greatly increased depth, evaluating models up to 152 layers deep on ImageNet at lower complexity than VGG networks. The approach won first place in the ILSVRC 2015 classification task and yielded large improvements on detection and localization benchmarks.
Key findings
- Identity shortcut connections let networks learn residual mappings, addressing the degradation problem and allowing successful training of networks far deeper than previously feasible.
- An ensemble of residual nets achieved 3.57% top-5 error on the ImageNet test set, winning 1st place in the ILSVRC 2015 classification competition.
- Deeper residual representations also produced a 28% relative improvement on the COCO object-detection dataset and 1st-place finishes across multiple ILSVRC and COCO 2015 tracks.
Subjects & keywords
Cite this paper
Kaiming He, Xiangyu Zhang, Shaoqing Ren, & Jian Sun (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2016.90
@inproceedings{he2016deep,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
booktitle = {2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2016},
doi = {10.1109/CVPR.2016.90},
url = {https://doi.org/10.1109/CVPR.2016.90}
}