# Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition

arXiv: https://arxiv.org/abs/2104.02424 · HTML: https://mlsanity.com/paper/2104.02424/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 6 Apr 2021.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [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)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [MVDepthNet: Real-time Multiview Depth Estimation Neural Network](https://mlsanity.com/paper/1807.08563/) (2018)
- [Bi3D: Stereo Depth Estimation via Binary Classifications](https://mlsanity.com/paper/2005.07274/) (2020)
- [Improving Shadow Suppression for Illumination Robust Face Recognition](https://mlsanity.com/paper/1710.05073/) (2017)
- [A Comprehensive Analysis of Deep Learning Based Representation for Face Recognition](https://mlsanity.com/paper/1606.02894/) (2016)
- [Robust RGB-D Face Recognition Using Attribute-Aware Loss](https://mlsanity.com/paper/1811.09847/) (2018)
- [Depth as Attention for Face Representation Learning](https://mlsanity.com/paper/2101.00652/) (2021)
- [Learning to Generate Facial Depth Maps](https://mlsanity.com/paper/1805.11927/) (2018)

## Built on by (most cited first, 4 of 4)

- [DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection](https://mlsanity.com/paper/2304.13031/) (2023)
- [Privacy-Preserving Remote Heart Rate Estimation from Facial Videos](https://mlsanity.com/paper/2306.01141/) (2023)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [Confidence-Aware RGB-D Face Recognition via Virtual Depth Synthesis](https://mlsanity.com/paper/2403.06529/) (2024)

## Abstract (arXiv)

We present the Teacher-Student Generative Adversarial Network (TS-GAN) to generate depth images from single RGB images in order to boost the performance of face recognition systems. For our method to generalize well across unseen datasets, we design two components in the architecture, a teacher and a student. The teacher, which itself consists of a generator and a discriminator, learns a latent mapping between input RGB and paired depth images in a supervised fashion. The student, which consists of two generators (one shared with the teacher) and a discriminator, learns from new RGB data with no available paired depth information, for improved generalization. The fully trained shared generator can then be used in runtime to hallucinate depth from RGB for downstream applications such as face recognition. We perform rigorous experiments to show the superiority of TS-GAN over other methods in generating synthetic depth images. Moreover, face recognition experiments demonstrate that our hallucinated depth along with the input RGB images boosts performance across various architectures when compared to a single RGB modality by average values of +1.2%, +2.6%, and +2.6% for IIIT-D, EURECOM, and LFW datasets respectively. We make our implementation public at: https://github.com/hardik-uppal/teacher-student-gan.git.