# A Performance Comparison of Loss Functions for Deep Face Recognition

arXiv: https://arxiv.org/abs/1901.05903 · HTML: https://mlsanity.com/paper/1901.05903/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jan 2019.

## Built on by (most cited first, 9 of 9)

- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark](https://mlsanity.com/paper/2109.14545/) (2021)
- [WSD: Wild Selfie Dataset for Face Recognition in Selfie Images](https://mlsanity.com/paper/2302.07245/) (2023)
- [Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognition](https://mlsanity.com/paper/2307.08417/) (2023)
- [Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Sampling](https://mlsanity.com/paper/2505.12048/) (2025)
- [Semantic Map Injected GAN Training for Image-to-Image Translation](https://mlsanity.com/paper/2112.01845/) (2021)
- [Robust Smart Home Face Recognition under Starving Federated Data](https://mlsanity.com/paper/2211.05410/) (2022)
- [Enhancing Face Recognition with Latent Space Data Augmentation and Facial Posture Reconstruction](https://mlsanity.com/paper/2301.11986/) (2023)
- [MSMA: Multi-Scale Feature Fusion For Multi-Attribute 3D Face Reconstruction From Unconstrained Images](https://mlsanity.com/paper/2509.11763/) (2025)

## Abstract (arXiv)

Face recognition is one of the most widely publicized feature in the devices today and hence represents an important problem that should be studied with the utmost priority. As per the recent trends, the Convolutional Neural Network (CNN) based approaches are highly successful in many tasks of Computer Vision including face recognition. The loss function is used on the top of CNN to judge the goodness of any network. In this paper, we present a performance comparison of different loss functions such as Cross-Entropy, Angular Softmax, Additive-Margin Softmax, ArcFace and Marginal Loss for face recognition. The experiments are conducted with two CNN architectures namely, ResNet and MobileNet. Two widely used face datasets namely, CASIA-Webface and MS-Celeb-1M are used for the training and benchmark Labeled Faces in the Wild (LFW) face dataset is used for the testing.