# KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition

arXiv: https://arxiv.org/abs/2201.07394 · HTML: https://mlsanity.com/paper/2201.07394/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 67 references that are in the map.
- First posted on arXiv 19 Jan 2022.

## Builds on (most cited first, 30 of 30)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [Gradient Harmonized Single-stage Detector](https://mlsanity.com/paper/1811.05181/) (2018)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition](https://mlsanity.com/paper/1712.04695/) (2017)
- [Mis-classified Vector Guided Softmax Loss for Face Recognition](https://mlsanity.com/paper/1912.00833/) (2019)
- [von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification](https://mlsanity.com/paper/1706.04264/) (2017)
- [Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos](https://mlsanity.com/paper/1811.00342/) (2018)
- [Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval](https://mlsanity.com/paper/1802.09662/) (2018)
- [P2SGrad: Refined Gradients for Optimizing Deep Face Models](https://mlsanity.com/paper/1905.02479/) (2019)
- [Multicolumn Networks for Face Recognition](https://mlsanity.com/paper/1807.09192/) (2018)

## Built on by (most cited first, 11 of 11)

- [3D GAN Inversion for Controllable Portrait Image Animation](https://mlsanity.com/paper/2203.13441/) (2022)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)
- [Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model](https://mlsanity.com/paper/2210.13664/) (2022)
- [Exploring the Learning Difficulty of Data Theory and Measure](https://mlsanity.com/paper/2205.07427/) (2022)
- [Learning Branched Fusion and Orthogonal Projection for Face-Voice Association](https://mlsanity.com/paper/2208.10238/) (2022)
- [2nd Place Solution to Google Landmark Retrieval 2020](https://mlsanity.com/paper/2210.01624/) (2022)
- [DAAL: Density-Aware Adaptive Line Margin Loss for Multi-Modal Deep Metric Learning](https://mlsanity.com/paper/2410.05438/) (2024)
- [Find the Differences: Differential Morphing Attack Detection vs Face Recognition](https://mlsanity.com/paper/2604.14734/) (2026)
- [MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection](https://mlsanity.com/paper/2605.10240/) (2026)
- [Sparsity-Inducing Divergence Losses for Biometric Verification](https://mlsanity.com/paper/2606.31664/) (2026)
- [DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching](https://mlsanity.com/paper/2609.16149/) (2026)

## Abstract (arXiv)

Feature learning is a widely used method employed for large-scale face recognition. Recently, large-margin softmax loss methods have demonstrated significant enhancements on deep face recognition. These methods propose fixed positive margins in order to enforce intra-class compactness and inter-class diversity. However, the majority of the proposed methods do not consider the class imbalance issue, which is a major challenge in practice for developing deep face recognition models. We hypothesize that it significantly affects the generalization ability of the deep face models. Inspired by this observation, we introduce a novel adaptive strategy, called KappaFace, to modulate the relative importance based on class difficultness and imbalance. With the support of the von Mises-Fisher distribution, our proposed KappaFace loss can intensify the margin's magnitude for hard learning or low concentration classes while relaxing it for counter classes. Experiments conducted on popular facial benchmarks demonstrate that our proposed method achieves superior performance to the state-of-the-art.