# PAM: Pose Attention Module for Pose-Invariant Face Recognition

arXiv: https://arxiv.org/abs/2111.11940 · HTML: https://mlsanity.com/paper/2111.11940/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 23 Nov 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis](https://mlsanity.com/paper/1704.04086/) (2017)
- [DeepID3: Face Recognition with Very Deep Neural Networks](https://mlsanity.com/paper/1502.00873/) (2015)
- [UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition](https://mlsanity.com/paper/1712.04695/) (2017)
- [Deeply learned face representations are sparse, selective, and robust](https://mlsanity.com/paper/1412.1265/) (2014)
- [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)

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

- [Pose Attention-Guided Profile-to-Frontal Face Recognition](https://mlsanity.com/paper/2209.07001/) (2022)
- [Pose-invariant face recognition via feature-space pose frontalization](https://mlsanity.com/paper/2505.16412/) (2025)
- [NeuroLip: An Event-driven Spatiotemporal Learning Framework for Cross-Scene Lip-Motion-based Visual Speaker Recognition](https://mlsanity.com/paper/2604.15718/) (2026)

## Abstract (arXiv)

Pose variation is one of the key challenges in face recognition. Conventional techniques mainly focus on face frontalization or face augmentation in image space. However, transforming face images in image space is not guaranteed to preserve the lossless identity features of the original image. Moreover, these methods suffer from more computational costs and memory requirements due to the additional models. We argue that it is more desirable to perform feature transformation in hierarchical feature space rather than image space, which can take advantage of different feature levels and benefit from joint learning with representation learning. To this end, we propose a lightweight and easy-to-implement attention block, named Pose Attention Module (PAM), for pose-invariant face recognition. Specifically, PAM performs frontal-profile feature transformation in hierarchical feature space by learning residuals between pose variations with a soft gate mechanism. We validated the effectiveness of PAM block design through extensive ablation studies and verified the performance on several popular benchmarks, including LFW, CFP-FP, AgeDB-30, CPLFW, and CALFW. Experimental results show that our method not only outperforms state-of-the-art methods but also effectively reduces memory requirements by more than 75 times. It is noteworthy that our method is not limited to face recognition with large pose variations. By adjusting the soft gate mechanism of PAM to a specific coefficient, such semantic attention block can easily extend to address other intra-class imbalance problems in face recognition, including large variations in age, illumination, expression, etc.