# Support Vector Guided Softmax Loss for Face Recognition

arXiv: https://arxiv.org/abs/1812.11317 · HTML: https://mlsanity.com/paper/1812.11317/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2018.

## Built on by (most cited first, 10 of 10)

- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [DigiFace-1M: 1 Million Digital Face Images for Face Recognition](https://mlsanity.com/paper/2210.02579/) (2022)
- [An Efficient Training Approach for Very Large Scale Face Recognition](https://mlsanity.com/paper/2105.10375/) (2021)
- [Recent Advances in Large Margin Learning](https://mlsanity.com/paper/2103.13598/) (2021)
- [PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition](https://mlsanity.com/paper/2107.11721/) (2021)
- [FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders](https://mlsanity.com/paper/2205.11090/) (2022)
- [X2-Softmax: Margin Adaptive Loss Function for Face Recognition](https://mlsanity.com/paper/2312.05281/) (2023)
- [Inter-class Discrepancy Alignment for Face Recognition](https://mlsanity.com/paper/2103.01559/) (2021)
- [A Dataset and Benchmark Towards Multi-Modal Face Anti-Spoofing Under Surveillance Scenarios](https://mlsanity.com/paper/2103.15409/) (2021)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)

## Abstract (arXiv)

Face recognition has witnessed significant progresses due to the advances of deep convolutional neural networks (CNNs), the central challenge of which, is feature discrimination. To address it, one group tries to exploit mining-based strategies (textite.g., hard example mining and focal loss) to focus on the informative examples. The other group devotes to designing margin-based loss functions (textite.g., angular, additive and additive angular margins) to increase the feature margin from the perspective of ground truth class. Both of them have been well-verified to learn discriminative features. However, they suffer from either the ambiguity of hard examples or the lack of discriminative power of other classes. In this paper, we design a novel loss function, namely support vector guided softmax loss (SV-Softmax), which adaptively emphasizes the mis-classified points (support vectors) to guide the discriminative features learning. So the developed SV-Softmax loss is able to eliminate the ambiguity of hard examples as well as absorb the discriminative power of other classes, and thus results in more discrimiantive features. To the best of our knowledge, this is the first attempt to inherit the advantages of mining-based and margin-based losses into one framework. Experimental results on several benchmarks have demonstrated the effectiveness of our approach over state-of-the-arts.