# CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

arXiv: https://arxiv.org/abs/2004.00288 · HTML: https://mlsanity.com/paper/2004.00288/

## Key facts

- Cited by 321 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 30 of 321)

- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models](https://mlsanity.com/paper/2302.12228/) (2023)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [PuLID: Pure and Lightning ID Customization via Contrastive Alignment](https://mlsanity.com/paper/2404.16022/) (2024)
- [Phantom: Subject-consistent video generation via cross-modal alignment](https://mlsanity.com/paper/2502.11079/) (2025)
- [DCFace: Synthetic Face Generation with Dual Condition Diffusion Model](https://mlsanity.com/paper/2304.07060/) (2023)
- [HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping](https://mlsanity.com/paper/2106.09965/) (2021)
- [DigiFace-1M: 1 Million Digital Face Images for Face Recognition](https://mlsanity.com/paper/2210.02579/) (2022)
- [HyperInverter: Improving StyleGAN Inversion via Hypernetwork](https://mlsanity.com/paper/2112.00719/) (2021)
- [DreamO: A Unified Framework for Image Customization](https://mlsanity.com/paper/2504.16915/) (2025)
- [HairCLIP: Design Your Hair by Text and Reference Image](https://mlsanity.com/paper/2112.05142/) (2021)
- [PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization](https://mlsanity.com/paper/2312.06354/) (2023)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation](https://mlsanity.com/paper/2505.20292/) (2025)
- [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://mlsanity.com/paper/2503.07065/) (2025)
- [CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability](https://mlsanity.com/paper/2112.06592/) (2021)
- [Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control](https://mlsanity.com/paper/2405.12970/) (2024)
- [BlendFace: Re-designing Identity Encoders for Face-Swapping](https://mlsanity.com/paper/2307.10854/) (2023)
- [SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Data](https://mlsanity.com/paper/2206.10520/) (2022)
- [Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2103.00236/) (2021)
- [Third Time's the Charm? Image and Video Editing with StyleGAN3](https://mlsanity.com/paper/2201.13433/) (2022)
- [Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input](https://mlsanity.com/paper/2203.09123/) (2022)
- [FaceX-Zoo: A PyTorch Toolbox for Face Recognition](https://mlsanity.com/paper/2101.04407/) (2021)
- [Face Animation with an Attribute-Guided Diffusion Model](https://mlsanity.com/paper/2304.03199/) (2023)
- [LCM-Lookahead for Encoder-based Text-to-Image Personalization](https://mlsanity.com/paper/2404.03620/) (2024)

## Abstract (arXiv)

As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability. More recently, the idea of mining-based strategies is adopted to emphasize the misclassified samples, achieving promising results. However, during the entire training process, the prior methods either do not explicitly emphasize the sample based on its importance that renders the hard samples not fully exploited; or explicitly emphasize the effects of semi-hard/hard samples even at the early training stage that may lead to convergence issue. In this work, we propose a novel Adaptive Curriculum Learning loss (CurricularFace) that embeds the idea of curriculum learning into the loss function to achieve a novel training strategy for deep face recognition, which mainly addresses easy samples in the early training stage and hard ones in the later stage. Specifically, our CurricularFace adaptively adjusts the relative importance of easy and hard samples during different training stages. In each stage, different samples are assigned with different importance according to their corresponding difficultness. Extensive experimental results on popular benchmarks demonstrate the superiority of our CurricularFace over the state-of-the-art competitors.