# A Light CNN for Deep Face Representation with Noisy Labels

arXiv: https://arxiv.org/abs/1511.02683 · HTML: https://mlsanity.com/paper/1511.02683/

## Key facts

- Cited by 126 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2015.

## Built on by (most cited first, 30 of 126)

- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [Breaking the Dilemma of Medical Image-to-image Translation](https://mlsanity.com/paper/2110.06465/) (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)
- [Black-box Dataset Ownership Verification via Backdoor Watermarking](https://mlsanity.com/paper/2209.06015/) (2022)
- [FaceX-Zoo: A PyTorch Toolbox for Face Recognition](https://mlsanity.com/paper/2101.04407/) (2021)
- [Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers](https://mlsanity.com/paper/2108.02922/) (2021)
- [Half-Truth: A Partially Fake Audio Detection Dataset](https://mlsanity.com/paper/2104.03617/) (2021)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [MixFaceNets: Extremely Efficient Face Recognition Networks](https://mlsanity.com/paper/2107.13046/) (2021)
- [EdgeFace: Efficient Face Recognition Model for Edge Devices](https://mlsanity.com/paper/2307.01838/) (2023)
- [Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image](https://mlsanity.com/paper/2403.09632/) (2024)
- [Green Learning: Introduction, Examples and Outlook](https://mlsanity.com/paper/2210.00965/) (2022)
- [Improved DeepFake Detection Using Whisper Features](https://mlsanity.com/paper/2306.01428/) (2023)
- [Face.evoLVe: A High-Performance Face Recognition Library](https://mlsanity.com/paper/2107.08621/) (2021)
- [Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning](https://mlsanity.com/paper/2112.00568/) (2021)
- [PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal](https://mlsanity.com/paper/2105.12324/) (2021)
- [Prepended Domain Transformer: Heterogeneous Face Recognition without Bells and Whistles](https://mlsanity.com/paper/2210.06529/) (2022)
- [ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection](https://mlsanity.com/paper/2505.11079/) (2025)
- [Leveraging Mixture of Experts for Improved Speech Deepfake Detection](https://mlsanity.com/paper/2409.16077/) (2024)
- [Multi-Target Multi-Camera Tracking of Vehicles using Metadata-Aided Re-ID and Trajectory-Based Camera Link Model](https://mlsanity.com/paper/2105.01213/) (2021)
- [RGB-D And Thermal Sensor Fusion: A Systematic Literature Review](https://mlsanity.com/paper/2305.11427/) (2023)
- [Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher](https://mlsanity.com/paper/2205.14361/) (2022)
- [Defense Against Adversarial Attacks on Audio DeepFake Detection](https://mlsanity.com/paper/2212.14597/) (2022)
- [Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models](https://mlsanity.com/paper/2108.06581/) (2021)
- [Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques](https://mlsanity.com/paper/2110.05044/) (2021)
- [Deep Rival Penalized Competitive Learning for Low-resolution Face Recognition](https://mlsanity.com/paper/2108.01286/) (2021)
- [An Examination of Bias of Facial Analysis based BMI Prediction Models](https://mlsanity.com/paper/2204.10262/) (2022)
- [Fully Automated End-to-End Fake Audio Detection](https://mlsanity.com/paper/2208.09618/) (2022)

## Abstract (arXiv)

The volume of convolutional neural network (CNN) models proposed for face recognition has been continuously growing larger to better fit large amount of training data. When training data are obtained from internet, the labels are likely to be ambiguous and inaccurate. This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels. First, we introduce a variation of maxout activation, called Max-Feature-Map (MFM), into each convolutional layer of CNN. Different from maxout activation that uses many feature maps to linearly approximate an arbitrary convex activation function, MFM does so via a competitive relationship. MFM can not only separate noisy and informative signals but also play the role of feature selection between two feature maps. Second, three networks are carefully designed to obtain better performance meanwhile reducing the number of parameters and computational costs. Lastly, a semantic bootstrapping method is proposed to make the prediction of the networks more consistent with noisy labels. Experimental results show that the proposed framework can utilize large-scale noisy data to learn a Light model that is efficient in computational costs and storage spaces. The learned single network with a 256-D representation achieves state-of-the-art results on various face benchmarks without fine-tuning. The code is released on https://github.com/AlfredXiangWu/LightCNN.