SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.02424 · ICCV · 2021

Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition

Ali Etemad, Michael Greenspan, Alireza Sepas-Moghaddam, Hardik Uppal

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 boost 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/hardikuppal/teacher-student-gan.git.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.02424")
get_code_for_paper("2104.02424")
have("2104.02424")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.02424.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.02424.svg)](https://syntology.ai/paper/2104.02424)

Connect an agent — have() is free.