# AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations

arXiv: https://arxiv.org/abs/1905.00292 · HTML: https://mlsanity.com/paper/1905.00292/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2019.

## Built on by (most cited first, 30 of 83)

- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [FaceX-Zoo: A PyTorch Toolbox for Face Recognition](https://mlsanity.com/paper/2101.04407/) (2021)
- [Learning Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2105.01017/) (2021)
- [Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation](https://mlsanity.com/paper/2210.04524/) (2022)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Face.evoLVe: A High-Performance Face Recognition Library](https://mlsanity.com/paper/2107.08621/) (2021)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition](https://mlsanity.com/paper/2205.12010/) (2022)
- [Knowledge Evolution in Neural Networks](https://mlsanity.com/paper/2103.05152/) (2021)
- [A Quality Aware Sample-to-Sample Comparison for Face Recognition](https://mlsanity.com/paper/2306.04000/) (2023)
- [Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model](https://mlsanity.com/paper/2210.13664/) (2022)
- [LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition](https://mlsanity.com/paper/2501.13420/) (2025)
- [KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2201.07394/) (2022)
- [IronMask: Modular Architecture for Protecting Deep Face Template](https://mlsanity.com/paper/2104.02239/) (2021)
- [RidgeBase: A Cross-Sensor Multi-Finger Contactless Fingerprint Dataset](https://mlsanity.com/paper/2307.05563/) (2023)
- [Eight Years of Face Recognition Research: Reproducibility, Achievements and Open Issues](https://mlsanity.com/paper/2208.04040/) (2022)
- [MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts](https://mlsanity.com/paper/2405.18979/) (2024)
- [PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition](https://mlsanity.com/paper/2107.11721/) (2021)
- [PETALface: Parameter Efficient Transfer Learning for Low-resolution Face Recognition](https://mlsanity.com/paper/2412.07771/) (2024)
- [BoundaryFace: A mining framework with noise label self-correction for Face Recognition](https://mlsanity.com/paper/2210.04567/) (2022)
- [CoNAN: Conditional Neural Aggregation Network For Unconstrained Face Feature Fusion](https://mlsanity.com/paper/2307.10237/) (2023)
- [DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models](https://mlsanity.com/paper/2509.13927/) (2025)
- [NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition](https://mlsanity.com/paper/2103.03503/) (2021)
- [Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition](https://mlsanity.com/paper/2209.04920/) (2022)

## Abstract (arXiv)

The cosine-based softmax losses and their variants achieve great success in deep learning based face recognition. However, hyperparameter settings in these losses have significant influences on the optimization path as well as the final recognition performance. Manually tuning those hyperparameters heavily relies on user experience and requires many training tricks. In this paper, we investigate in depth the effects of two important hyperparameters of cosine-based softmax losses, the scale parameter and angular margin parameter, by analyzing how they modulate the predicted classification probability. Based on these analysis, we propose a novel cosine-based softmax loss, AdaCos, which is hyperparameter-free and leverages an adaptive scale parameter to automatically strengthen the training supervisions during the training process. We apply the proposed AdaCos loss to large-scale face verification and identification datasets, including LFW, MegaFace, and IJB-C 1:1 Verification. Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy. Our method outperforms state-of-the-art softmax losses on all the three datasets.