Large-Margin Softmax Loss for Convolutional Neural Networks

@inproceedings{Liu2016LargeMarginSL,
  title={Large-Margin Softmax Loss for Convolutional Neural Networks},
  author={Weiyang Liu and Yandong Wen and Zhiding Yu and Meng Meng Yang},
  booktitle={ICML},
  year={2016}
}
Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages intra-class compactness and inter-class separability between learned features. Moreover, L-Softmax not… CONTINUE READING
Highly Influential
This paper has highly influenced 19 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 145 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 17 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 99 extracted citations

Ensemble Soft-Margin Softmax Loss for Image Classification

IJCAI • 2018
View 20 Excerpts
Highly Influenced

AF-Softmax for Face Recognition

2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC) • 2018
View 5 Excerpts
Highly Influenced

Deep Face Recognition: A Survey

ArXiv • 2018
View 10 Excerpts
Highly Influenced

Large-scale Bisample Learning on ID vs. Spot Face Recognition

ArXiv • 2018
View 4 Excerpts
Highly Influenced

On the Geometry of Adversarial Examples

View 4 Excerpts
Highly Influenced

Convolutional neural networks with large-margin softmax loss function for cognitive load recognition

2017 36th Chinese Control Conference (CCC) • 2017
View 6 Excerpts
Highly Influenced

145 Citations

050100201720182019
Citations per Year
Semantic Scholar estimates that this publication has 145 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 34 references

The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]

IEEE Signal Processing Magazine • 2012
View 6 Excerpts
Highly Influenced

FaceNet: A unified embedding for face recognition and clustering

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 6 Excerpts
Highly Influenced

Deep Residual Learning for Image Recognition

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 5 Excerpts
Highly Influenced

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

2015 IEEE International Conference on Computer Vision (ICCV) • 2015
View 5 Excerpts
Highly Influenced

Going deeper with convolutions

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…