# Additive Margin Softmax for Face Verification

arXiv: https://arxiv.org/abs/1801.05599 · HTML: https://mlsanity.com/paper/1801.05599/

## Key facts

- Cited by 278 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2018.

## Built on by (most cited first, 30 of 278)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [Generalizing Face Forgery Detection with High-frequency Features](https://mlsanity.com/paper/2103.12376/) (2021)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection](https://mlsanity.com/paper/2203.12208/) (2022)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [Label-Imbalanced and Group-Sensitive Classification under Overparameterization](https://mlsanity.com/paper/2103.01550/) (2021)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition](https://mlsanity.com/paper/2203.14325/) (2022)
- [Tackling Data Heterogeneity in Federated Learning with Class Prototypes](https://mlsanity.com/paper/2212.02758/) (2022)
- [AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding](https://mlsanity.com/paper/2405.03121/) (2024)
- [RSG: A Simple but Effective Module for Learning Imbalanced Datasets](https://mlsanity.com/paper/2106.09859/) (2021)
- [FaceX-Zoo: A PyTorch Toolbox for Face Recognition](https://mlsanity.com/paper/2101.04407/) (2021)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2105.14289/) (2021)
- [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Masked Face Recognition Challenge: The InsightFace Track Report](https://mlsanity.com/paper/2108.08191/) (2021)
- [RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition](https://mlsanity.com/paper/2105.01883/) (2021)
- [Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset](https://mlsanity.com/paper/2203.16844/) (2022)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [Generalized Neural Collapse for a Large Number of Classes](https://mlsanity.com/paper/2310.05351/) (2023)
- [Learning with Hyperspherical Uniformity](https://mlsanity.com/paper/2103.01649/) (2021)
- [Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation](https://mlsanity.com/paper/2102.10365/) (2021)
- [Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.06094/) (2021)
- [DASB - Discrete Audio and Speech Benchmark](https://mlsanity.com/paper/2406.14294/) (2024)
- [FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting](https://mlsanity.com/paper/2105.07147/) (2021)

## Abstract (arXiv)

In this paper, we propose a conceptually simple and geometrically interpretable objective function, i.e. additive margin Softmax (AM-Softmax), for deep face verification. In general, the face verification task can be viewed as a metric learning problem, so learning large-margin face features whose intra-class variation is small and inter-class difference is large is of great importance in order to achieve good performance. Recently, Large-margin Softmax and Angular Softmax have been proposed to incorporate the angular margin in a multiplicative manner. In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works. We also emphasize and discuss the importance of feature normalization in the paper. Most importantly, our experiments on LFW BLUFR and MegaFace show that our additive margin softmax loss consistently performs better than the current state-of-the-art methods using the same network architecture and training dataset. Our code has also been made available at https://github.com/happynear/AMSoftmax