# Attribute-Guided Coupled GAN for Cross-Resolution Face Recognition

## TL;DR

This paper introduces a novel attribute-guided coupled GAN framework for cross-resolution face recognition, effectively aligning low- and high-resolution images in a shared embedding space by leveraging facial attributes.

## Contribution

The paper presents a new coupled GAN architecture that incorporates facial attribute prediction to enhance cross-resolution face recognition performance.

## Key findings

- Outperforms state-of-the-art methods on multiple datasets.
- Effectively aligns low- and high-resolution images in a common embedding space.
- Utilizes facial attributes to improve discriminative power.

## Abstract

In this paper, we propose a novel attribute-guided cross-resolution (low-resolution to high-resolution) face recognition framework that leverages a coupled generative adversarial network (GAN) structure with adversarial training to find the hidden relationship between the low-resolution and high-resolution images in a latent common embedding subspace. The coupled GAN framework consists of two sub-networks, one dedicated to the low-resolution domain and the other dedicated to the high-resolution domain. Each sub-network aims to find a projection that maximizes the pair-wise correlation between the two feature domains in a common embedding subspace. In addition to projecting the images into a common subspace, the coupled network also predicts facial attributes to improve the cross-resolution face recognition. Specifically, our proposed coupled framework exploits facial attributes to further maximize the pair-wise correlation by implicitly matching facial attributes of the low and high-resolution images during the training, which leads to a more discriminative embedding subspace resulting in performance enhancement for cross-resolution face recognition. The efficacy of our approach compared with the state-of-the-art is demonstrated using the LFWA, Celeb-A, SCFace and UCCS datasets.