# RepFace: Refining Closed-Set Noise with Progressive Label Correction for Face Recognition

arXiv: https://arxiv.org/abs/2412.12031 · HTML: https://mlsanity.com/paper/2412.12031/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [The Devil of Face Recognition is in the Noise](https://mlsanity.com/paper/1807.11649/) (2018)
- [Mis-classified Vector Guided Softmax Loss for Face Recognition](https://mlsanity.com/paper/1912.00833/) (2019)
- [Open-set Label Noise Can Improve Robustness Against Inherent Label Noise](https://mlsanity.com/paper/2106.10891/) (2021)
- [Improved Residual Networks for Image and Video Recognition](https://mlsanity.com/paper/2004.04989/) (2020)
- [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Noise-Tolerant Paradigm for Training Face Recognition CNNs](https://mlsanity.com/paper/1903.10357/) (2019)
- [Part-based Face Recognition with Vision Transformers](https://mlsanity.com/paper/2212.00057/) (2022)
- [A Quality Aware Sample-to-Sample Comparison for Face Recognition](https://mlsanity.com/paper/2306.04000/) (2023)
- [Racial Faces in-the-Wild: Reducing Racial Bias by Information Maximization Adaptation Network](https://mlsanity.com/paper/1812.00194/) (2018)
- [BoundaryFace: A mining framework with noise label self-correction for Face Recognition](https://mlsanity.com/paper/2210.04567/) (2022)

## Built on by (most cited first, 1 of 1)

- [Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets](https://mlsanity.com/paper/2605.29720/) (2026)

## Abstract (arXiv)

Face recognition has made remarkable strides, driven by the expanding scale of datasets, advancements in various backbone and discriminative losses. However, face recognition performance is heavily affected by the label noise, especially closed-set noise. While numerous studies have focused on handling label noise, addressing closed-set noise still poses challenges. This paper identifies this challenge as training isn't robust to noise at the early-stage training, and necessitating an appropriate learning strategy for samples with low confidence, which are often misclassified as closed-set noise in later training phases. To address these issues, we propose a new framework to stabilize the training at early stages and split the samples into clean, ambiguous and noisy groups which are devised with separate training strategies. Initially, we employ generated auxiliary closed-set noisy samples to enable the model to identify noisy data at the early stages of training. Subsequently, we introduce how samples are split into clean, ambiguous and noisy groups by their similarity to the positive and nearest negative centers. Then we perform label fusion for ambiguous samples by incorporating accumulated model predictions. Finally, we apply label smoothing within the closed set, adjusting the label to a point between the nearest negative class and the initially assigned label. Extensive experiments validate the effectiveness of our method on mainstream face datasets, achieving state-of-the-art results. The code will be released upon acceptance.