# Ring loss: Convex Feature Normalization for Face Recognition

## TL;DR

Ring loss introduces a convex feature normalization method for deep networks that improves face recognition performance by ensuring uniform class representation and robustness across various challenging datasets.

## Contribution

The paper proposes Ring loss, a novel soft normalization technique that maintains convexity, enhancing deep feature normalization for face recognition tasks.

## Key findings

- Outperforms strong baselines on large-scale face recognition datasets.
- Achieves state-of-the-art results on Janus CS3.
- Improves low-resolution face matching performance.

## Abstract

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.