# von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification

arXiv: https://arxiv.org/abs/1706.04264 · HTML: https://mlsanity.com/paper/1706.04264/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2017.

## Built on by (most cited first, 30 of 46)

- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Compressive Visual Representations](https://mlsanity.com/paper/2109.12909/) (2021)
- [Non-isotropy Regularization for Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2203.08547/) (2022)
- [Transductive Zero-Shot and Few-Shot CLIP](https://mlsanity.com/paper/2405.18437/) (2024)
- [Regular Polytope Networks](https://mlsanity.com/paper/2103.15632/) (2021)
- [A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2207.03784/) (2022)
- [ID3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition](https://mlsanity.com/paper/2409.17576/) (2024)
- [Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning](https://mlsanity.com/paper/2208.10043/) (2022)
- [DINO as a von Mises-Fisher mixture model](https://mlsanity.com/paper/2405.10939/) (2024)
- [FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing](https://mlsanity.com/paper/2509.22412/) (2025)
- [Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model](https://mlsanity.com/paper/2210.13664/) (2022)
- [KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2201.07394/) (2022)
- [Probabilistic Embeddings Revisited](https://mlsanity.com/paper/2202.06768/) (2022)
- [Generalized Inter-class Loss for Gait Recognition](https://mlsanity.com/paper/2210.06779/) (2022)
- [Visualizing the Emergence of Intermediate Visual Patterns in DNNs](https://mlsanity.com/paper/2111.03505/) (2021)
- [Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances](https://mlsanity.com/paper/2206.03230/) (2022)
- [Maximally Compact and Separated Features with Regular Polytope Networks](https://mlsanity.com/paper/2301.06116/) (2023)
- [Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning](https://mlsanity.com/paper/2306.03364/) (2023)
- [Your Classifier Can Be Secretly a Likelihood-Based OOD Detector](https://mlsanity.com/paper/2408.04851/) (2024)
- [On The Distribution of Penultimate Activations of Classification Networks](https://mlsanity.com/paper/2107.01900/) (2021)
- [No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection](https://mlsanity.com/paper/2203.10344/) (2022)
- [Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition](https://mlsanity.com/paper/2211.07245/) (2022)
- [A Bayesian Approach to OOD Robustness in Image Classification](https://mlsanity.com/paper/2403.07277/) (2024)
- [Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres](https://mlsanity.com/paper/2506.10576/) (2025)
- [Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings](https://mlsanity.com/paper/2203.14893/) (2022)
- [Self-supervised learning with rotation-invariant kernels](https://mlsanity.com/paper/2208.00789/) (2022)
- [On Kernel-based Variational Autoencoder](https://mlsanity.com/paper/2405.12783/) (2024)
- [Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.08091/) (2024)
- [MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenes](https://mlsanity.com/paper/2304.12592/) (2023)
- [Dynamic Feature Learning and Matching for Class-Incremental Learning](https://mlsanity.com/paper/2405.08533/) (2024)

## Abstract (arXiv)

A number of pattern recognition tasks, textite.g., face verification, can be boiled down to classification or clustering of unit length directional feature vectors whose distance can be simply computed by their angle. In this paper, we propose the von Mises-Fisher (vMF) mixture model as the theoretical foundation for an effective deep-learning of such directional features and derive a novel vMF Mixture Loss and its corresponding vMF deep features. The proposed vMF feature learning achieves the characteristics of discriminative learning, textiti.e., compacting the instances of the same class while increasing the distance of instances from different classes. Moreover, it subsumes a number of popular loss functions as well as an effective method in deep learning, namely normalization. We conduct extensive experiments on face verification using 4 different challenging face datasets, textiti.e., LFW, YouTube faces, CACD and IJB-A. Results show the effectiveness and excellent generalization ability of the proposed approach as it achieves state-of-the-art results on the LFW, YouTube faces and CACD datasets and competitive results on the IJB-A dataset.