# Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation

arXiv: https://arxiv.org/abs/2409.12385 · HTML: https://mlsanity.com/paper/2409.12385/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 62 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Data Distillation: Towards Omni-Supervised Learning](https://mlsanity.com/paper/1712.04440/) (2017)
- [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)
- [Learning Metrics from Teachers: Compact Networks for Image Embedding](https://mlsanity.com/paper/1904.03624/) (2019)
- [Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion](https://mlsanity.com/paper/1905.11826/) (2019)
- [Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification](https://mlsanity.com/paper/1908.06052/) (2019)
- [Adapting Models to Signal Degradation using Distillation](https://mlsanity.com/paper/1604.00433/) (2016)
- [DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification](https://mlsanity.com/paper/1611.05271/) (2016)
- [Does Generative Face Completion Help Face Recognition?](https://mlsanity.com/paper/1906.02858/) (2019)

## Built on by (most cited first, 2 of 2)

- [Inclusive Review on Advances in Masked Human Face Recognition Technologies](https://mlsanity.com/paper/2508.00841/) (2025)
- [Masked Face Recognition under Different Backbones](https://mlsanity.com/paper/2601.16440/) (2026)

## Abstract (arXiv)

Many real-world applications today like video surveillance and urban governance need to address the recognition of masked faces, where content replacement by diverse masks often brings in incomplete appearance and ambiguous representation, leading to a sharp drop in accuracy. Inspired by recent progress on amodal perception, we propose to migrate the mechanism of amodal completion for the task of masked face recognition with an end-to-end de-occlusion distillation framework, which consists of two modules. The textitde-occlusion module applies a generative adversarial network to perform face completion, which recovers the content under the mask and eliminates appearance ambiguity. The textitdistillation module takes a pre-trained general face recognition model as the teacher and transfers its knowledge to train a student for completed faces using massive online synthesized face pairs. Especially, the teacher knowledge is represented with structural relations among instances in multiple orders, which serves as a posterior regularization to enable the adaptation. In this way, the knowledge can be fully distilled and transferred to identify masked faces. Experiments on synthetic and realistic datasets show the efficacy of the proposed approach.