# Median Pixel Difference Convolutional Network for Robust Face Recognition

arXiv: https://arxiv.org/abs/2205.15867 · HTML: https://mlsanity.com/paper/2205.15867/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 30 May 2022.

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

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Real Image Denoising with Feature Attention](https://mlsanity.com/paper/1904.07396/) (2019)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Learning From Noisy Large-Scale Datasets With Minimal Supervision](https://mlsanity.com/paper/1701.01619/) (2017)
- [Learning Warped Guidance for Blind Face Restoration](https://mlsanity.com/paper/1804.04829/) (2018)
- [Unpaired Learning of Deep Image Denoising](https://mlsanity.com/paper/2008.13711/) (2020)
- [The Devil of Face Recognition is in the Noise](https://mlsanity.com/paper/1807.11649/) (2018)
- [From BoW to CNN: Two Decades of Texture Representation for Texture Classification](https://mlsanity.com/paper/1801.10324/) (2018)
- [Local Binary Convolutional Neural Networks](https://mlsanity.com/paper/1608.06049/) (2016)
- [Pose-Robust Face Recognition via Deep Residual Equivariant Mapping](https://mlsanity.com/paper/1803.00839/) (2018)
- [Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing](https://mlsanity.com/paper/1904.06400/) (2019)
- [Noise-Tolerant Paradigm for Training Face Recognition CNNs](https://mlsanity.com/paper/1903.10357/) (2019)
- [Deep Face Deblurring](https://mlsanity.com/paper/1704.08772/) (2017)
- [Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification](https://mlsanity.com/paper/1709.03654/) (2017)
- [LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences](https://mlsanity.com/paper/1904.07647/) (2019)
- [MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild](https://mlsanity.com/paper/1805.09749/) (2018)

## Built on by (most cited first, 3 of 3)

- [Uncertain Facial Expression Recognition via Multi-task Assisted Correction](https://mlsanity.com/paper/2212.07144/) (2022)
- [Rapid Salient Object Detection with Difference Convolutional Neural Networks](https://mlsanity.com/paper/2507.01182/) (2025)
- [From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2303.08414/) (2023)

## Abstract (arXiv)

Face recognition is one of the most active tasks in computer vision and has been widely used in the real world. With great advances made in convolutional neural networks (CNN), lots of face recognition algorithms have achieved high accuracy on various face datasets. However, existing face recognition algorithms based on CNNs are vulnerable to noise. Noise corrupted image patterns could lead to false activations, significantly decreasing face recognition accuracy in noisy situations. To equip CNNs with built-in robustness to noise of different levels, we proposed a Median Pixel Difference Convolutional Network (MeDiNet) by replacing some traditional convolutional layers with the proposed novel Median Pixel Difference Convolutional Layer (MeDiConv) layer. The proposed MeDiNet integrates the idea of traditional multiscale median filtering with deep CNNs. The MeDiNet is tested on the four face datasets (LFW, CA-LFW, CP-LFW, and YTF) with versatile settings on blur kernels, noise intensities, scales, and JPEG quality factors. Extensive experiments show that our MeDiNet can effectively remove noisy pixels in the feature map and suppress the negative impact of noise, leading to achieving limited accuracy loss under these practical noises compared with the standard CNN under clean conditions.