# Seeing through the Mask: Multi-task Generative Mask Decoupling Face Recognition

arXiv: https://arxiv.org/abs/2311.11512 · HTML: https://mlsanity.com/paper/2311.11512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [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)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](https://mlsanity.com/paper/1803.07835/) (2018)
- [StructureFlow: Image Inpainting via Structure-aware Appearance Flow](https://mlsanity.com/paper/1908.03852/) (2019)
- [Generative Face Completion](https://mlsanity.com/paper/1704.05838/) (2017)
- [Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Network](https://mlsanity.com/paper/1908.06290/) (2019)
- [FaceX-Zoo: A PyTorch Toolbox for Face Recognition](https://mlsanity.com/paper/2101.04407/) (2021)
- [Masked Face Recognition for Secure Authentication](https://mlsanity.com/paper/2008.11104/) (2020)
- [WaveFill: A Wavelet-based Generation Network for Image Inpainting](https://mlsanity.com/paper/2107.11027/) (2021)
- [When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework](https://mlsanity.com/paper/2103.01520/) (2021)
- [End2End Occluded Face Recognition by Masking Corrupted Features](https://mlsanity.com/paper/2108.09468/) (2021)
- [Robust LSTM-Autoencoders for Face De-Occlusion in the Wild](https://mlsanity.com/paper/1612.08534/) (2016)
- [MLFW: A Database for Face Recognition on Masked Faces](https://mlsanity.com/paper/2109.05804/) (2021)
- [Mask-invariant Face Recognition through Template-level Knowledge Distillation](https://mlsanity.com/paper/2112.05646/) (2021)
- [NPCFace: Negative-Positive Collaborative Training for Large-scale Face Recognition](https://mlsanity.com/paper/2007.10172/) (2020)

## Abstract (arXiv)

The outbreak of COVID-19 pandemic make people wear masks more frequently than ever. Current general face recognition system suffers from serious performance degradation,when encountering occluded scenes. The potential reason is that face features are corrupted by occlusions on key facial regions. To tackle this problem, previous works either extract identity-related embeddings on feature level by additional mask prediction, or restore the occluded facial part by generative models. However, the former lacks visual results for model interpretation, while the latter suffers from artifacts which may affect downstream recognition. Therefore, this paper proposes a Multi-task gEnerative mask dEcoupling face Recognition (MEER) network to jointly handle these two tasks, which can learn occlusionirrelevant and identity-related representation while achieving unmasked face synthesis. We first present a novel mask decoupling module to disentangle mask and identity information, which makes the network obtain purer identity features from visible facial components. Then, an unmasked face is restored by a joint-training strategy, which will be further used to refine the recognition network with an id-preserving loss. Experiments on masked face recognition under realistic and synthetic occlusions benchmarks demonstrate that the MEER can outperform the state-ofthe-art methods.