# Pose Attention-Guided Profile-to-Frontal Face Recognition

arXiv: https://arxiv.org/abs/2209.07001 · HTML: https://mlsanity.com/paper/2209.07001/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 15 Sep 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Fine-Grained Head Pose Estimation Without Keypoints](https://mlsanity.com/paper/1710.00925/) (2017)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [Towards Universal Representation Learning for Deep Face Recognition](https://mlsanity.com/paper/2002.11841/) (2020)
- [Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis](https://mlsanity.com/paper/1704.04086/) (2017)
- [Towards Large-Pose Face Frontalization in the Wild](https://mlsanity.com/paper/1704.06244/) (2017)
- [Effective Face Frontalization in Unconstrained Images](https://mlsanity.com/paper/1411.7964/) (2014)
- [Pose-Robust Face Recognition via Deep Residual Equivariant Mapping](https://mlsanity.com/paper/1803.00839/) (2018)
- [Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis](https://mlsanity.com/paper/1601.00706/) (2016)
- [Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition](https://mlsanity.com/paper/1702.04710/) (2017)
- [CR-GAN: Learning Complete Representations for Multi-view Generation](https://mlsanity.com/paper/1806.11191/) (2018)
- [Triplet Probabilistic Embedding for Face Verification and Clustering](https://mlsanity.com/paper/1604.05417/) (2016)
- [Unconstrained Face Verification using Deep CNN Features](https://mlsanity.com/paper/1508.01722/) (2015)
- [Dual-Attention GAN for Large-Pose Face Frontalization](https://mlsanity.com/paper/2002.07227/) (2020)
- [A Comprehensive Survey on Pose-Invariant Face Recognition](https://mlsanity.com/paper/1502.04383/) (2015)
- [PF-cpGAN: Profile to Frontal Coupled GAN for Face Recognition in the Wild](https://mlsanity.com/paper/2005.02166/) (2020)
- [PAM: Pose Attention Module for Pose-Invariant Face Recognition](https://mlsanity.com/paper/2111.11940/) (2021)
- [Attention-guided Progressive Mapping for Profile Face Recognition](https://mlsanity.com/paper/2106.14124/) (2021)

## Built on by (most cited first, 3 of 3)

- [A Quality Aware Sample-to-Sample Comparison for Face Recognition](https://mlsanity.com/paper/2306.04000/) (2023)
- [Weakly Supervised Face and Whole Body Recognition in Turbulent Environments](https://mlsanity.com/paper/2308.11757/) (2023)
- [Pose-invariant face recognition via feature-space pose frontalization](https://mlsanity.com/paper/2505.16412/) (2025)

## Abstract (arXiv)

In recent years, face recognition systems have achieved exceptional success due to promising advances in deep learning architectures. However, they still fail to achieve expected accuracy when matching profile images against a gallery of frontal images. Current approaches either perform pose normalization (i.e., frontalization) or disentangle pose information for face recognition. We instead propose a new approach to utilize pose as an auxiliary information via an attention mechanism. In this paper, we hypothesize that pose attended information using an attention mechanism can guide contextual and distinctive feature extraction from profile faces, which further benefits a better representation learning in an embedded domain. To achieve this, first, we design a unified coupled profile-to-frontal face recognition network. It learns the mapping from faces to a compact embedding subspace via a class-specific contrastive loss. Second, we develop a novel pose attention block (PAB) to specially guide the pose-agnostic feature extraction from profile faces. To be more specific, PAB is designed to explicitly help the network to focus on important features along both channel and spatial dimension while learning discriminative yet pose invariant features in an embedding subspace. To validate the effectiveness of our proposed method, we conduct experiments on both controlled and in the wild benchmarks including Multi-PIE, CFP, IJBC, and show superiority over the state of the arts.