# When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition

arXiv: https://arxiv.org/abs/1504.02351 · HTML: https://mlsanity.com/paper/1504.02351/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2015.

## Built on by (most cited first, 21 of 21)

- [Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead](https://mlsanity.com/paper/2101.02559/) (2021)
- [Robust Backdoor Attacks against Deep Neural Networks in Real Physical World](https://mlsanity.com/paper/2104.07395/) (2021)
- [Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI](https://mlsanity.com/paper/2312.14229/) (2023)
- [ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection](https://mlsanity.com/paper/2312.14227/) (2023)
- [CapsField: Light Field-based Face and Expression Recognition in the Wild using Capsule Routing](https://mlsanity.com/paper/2101.03503/) (2021)
- [Natural Gradient Methods: Perspectives, Efficient-Scalable Approximations, and Analysis](https://mlsanity.com/paper/2303.05473/) (2023)
- [ZKROWNN: Zero Knowledge Right of Ownership for Neural Networks](https://mlsanity.com/paper/2309.06779/) (2023)
- [Depth as Attention for Face Representation Learning](https://mlsanity.com/paper/2101.00652/) (2021)
- [Masked Face Recognition using ResNet-50](https://mlsanity.com/paper/2104.08997/) (2021)
- [Towards Fairness-Aware Multi-Objective Optimization](https://mlsanity.com/paper/2207.12138/) (2022)
- [Evaluating the Robustness of Test Selection Methods for Deep Neural Networks](https://mlsanity.com/paper/2308.01314/) (2023)
- [Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis](https://mlsanity.com/paper/2409.16057/) (2024)
- [Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications](https://mlsanity.com/paper/2403.17787/) (2024)
- [ChannelExplorer: Exploring Class Separability Through Activation Channel Visualization](https://mlsanity.com/paper/2505.04647/) (2025)
- [A Survey on Face Recognition Systems](https://mlsanity.com/paper/2201.02991/) (2022)
- [A recipe of training neural network-based LDPC decoders](https://mlsanity.com/paper/2205.00481/) (2022)
- [POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices](https://mlsanity.com/paper/2205.09045/) (2022)
- [The Spike Gating Flow: A Hierarchical Structure Based Spiking Neural Network for Online Gesture Recognition](https://mlsanity.com/paper/2206.01910/) (2022)
- [CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network](https://mlsanity.com/paper/2407.09550/) (2024)
- [Attention-Guided Multi-scale Interaction Network for Face Super-Resolution](https://mlsanity.com/paper/2409.00591/) (2024)
- [Enhancing Classification with Semi-Supervised Deep Learning Using Distance-Based Sample Weights](https://mlsanity.com/paper/2505.14345/) (2025)

## Abstract (arXiv)

Deep learning, in particular Convolutional Neural Network (CNN), has achieved promising results in face recognition recently. However, it remains an open question: why CNNs work well and how to design a 'good' architecture. The existing works tend to focus on reporting CNN architectures that work well for face recognition rather than investigate the reason. In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible. Specifically, we use public database LFW (Labeled Faces in the Wild) to train CNNs, unlike most existing CNNs trained on private databases. We propose three CNN architectures which are the first reported architectures trained using LFW data. This paper quantitatively compares the architectures of CNNs and evaluate the effect of different implementation choices. We identify several useful properties of CNN-FRS. For instance, the dimensionality of the learned features can be significantly reduced without adverse effect on face recognition accuracy. In addition, traditional metric learning method exploiting CNN-learned features is evaluated. Experiments show two crucial factors to good CNN-FRS performance are the fusion of multiple CNNs and metric learning. To make our work reproducible, source code and models will be made publicly available.