# Ring loss: Convex Feature Normalization for Face Recognition

arXiv: https://arxiv.org/abs/1803.00130 · HTML: https://mlsanity.com/paper/1803.00130/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2018.

## Built on by (most cited first, 30 of 39)

- [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021)
- [Partner-Assisted Learning for Few-Shot Image Classification](https://mlsanity.com/paper/2109.07607/) (2021)
- [Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://mlsanity.com/paper/2110.10101/) (2021)
- [Variational Graph Normalized Auto-Encoders](https://mlsanity.com/paper/2108.08046/) (2021)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition](https://mlsanity.com/paper/2205.12010/) (2022)
- [Maximum Class Separation as Inductive Bias in One Matrix](https://mlsanity.com/paper/2206.08704/) (2022)
- [SphereFed: Hyperspherical Federated Learning](https://mlsanity.com/paper/2207.09413/) (2022)
- [Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining](https://mlsanity.com/paper/2210.08375/) (2022)
- [Deep transfer learning for image classification: a survey](https://mlsanity.com/paper/2205.09904/) (2022)
- [CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2410.05627/) (2024)
- [Eight Years of Face Recognition Research: Reproducibility, Achievements and Open Issues](https://mlsanity.com/paper/2208.04040/) (2022)
- [Escaping the Gradient Vanishing: Periodic Alternatives of Softmax in Attention Mechanism](https://mlsanity.com/paper/2108.07153/) (2021)
- [CoReFace: Sample-Guided Contrastive Regularization for Deep Face Recognition](https://mlsanity.com/paper/2304.11668/) (2023)
- [A Survey on Natural Language Video Localization](https://mlsanity.com/paper/2104.00234/) (2021)
- [Recent Advances in Deep Learning Techniques for Face Recognition](https://mlsanity.com/paper/2103.10492/) (2021)
- [Efficient Low-Resolution Face Recognition via Bridge Distillation](https://mlsanity.com/paper/2409.11786/) (2024)
- [Deep Domain Generalization with Feature-norm Network](https://mlsanity.com/paper/2104.13581/) (2021)
- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning](https://mlsanity.com/paper/2105.04113/) (2021)
- [Deep face recognition with clustering based domain adaptation](https://mlsanity.com/paper/2205.13937/) (2022)
- [Source-Free Unsupervised Domain Adaptation with Norm and Shape Constraints for Medical Image Segmentation](https://mlsanity.com/paper/2209.01300/) (2022)
- [Intra-Class Uncertainty Loss Function for Classification](https://mlsanity.com/paper/2104.05298/) (2021)
- [Quality-Aware Multimodal Biometric Recognition](https://mlsanity.com/paper/2112.05827/) (2021)
- [Activation Template Matching Loss for Explainable Face Recognition](https://mlsanity.com/paper/2207.02179/) (2022)
- [Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections](https://mlsanity.com/paper/2105.03139/) (2021)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [Open-Set Source Tracing as Compositional Factors via Structured Prototypes](https://mlsanity.com/paper/2607.03134/) (2026)

## Abstract (arXiv)

We motivate and present Ring loss, a simple and elegant feature normalization approach for deep networks designed to augment standard loss functions such as Softmax. We argue that deep feature normalization is an important aspect of supervised classification problems where we require the model to represent each class in a multi-class problem equally well. The direct approach to feature normalization through the hard normalization operation results in a non-convex formulation. Instead, Ring loss applies soft normalization, where it gradually learns to constrain the norm to the scaled unit circle while preserving convexity leading to more robust features. We apply Ring loss to large-scale face recognition problems and present results on LFW, the challenging protocols of IJB-A Janus, Janus CS3 (a superset of IJB-A Janus), Celebrity Frontal-Profile (CFP) and MegaFace with 1 million distractors. Ring loss outperforms strong baselines, matches state-of-the-art performance on IJB-A Janus and outperforms all other results on the challenging Janus CS3 thereby achieving state-of-the-art. We also outperform strong baselines in handling extremely low resolution face matching.