# Attention-guided Progressive Mapping for Profile Face Recognition

arXiv: https://arxiv.org/abs/2106.14124 · HTML: https://mlsanity.com/paper/2106.14124/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 27 Jun 2021.

## Builds on (most cited first, 19 of 19)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Decoupling "when to update" from "how to update"](https://mlsanity.com/paper/1706.02613/) (2017)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [Towards Universal Representation Learning for Deep Face Recognition](https://mlsanity.com/paper/2002.11841/) (2020)
- [UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition](https://mlsanity.com/paper/1712.04695/) (2017)
- [Mis-classified Vector Guided Softmax Loss for Face Recognition](https://mlsanity.com/paper/1912.00833/) (2019)
- [Pose-Robust Face Recognition via Deep Residual Equivariant Mapping](https://mlsanity.com/paper/1803.00839/) (2018)
- [Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition](https://mlsanity.com/paper/1702.04710/) (2017)
- [Reconstruction-Based Disentanglement for Pose-invariant Face Recognition](https://mlsanity.com/paper/1702.03041/) (2017)
- [A Comprehensive Survey on Pose-Invariant Face Recognition](https://mlsanity.com/paper/1502.04383/) (2015)
- [CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-identification](https://mlsanity.com/paper/1906.04976/) (2019)

## Built on by (most cited first, 2 of 2)

- [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)

## Abstract (arXiv)

The past few years have witnessed great progress in the domain of face recognition thanks to advances in deep learning. However, cross pose face recognition remains a significant challenge. It is difficult for many deep learning algorithms to narrow the performance gap caused by pose variations; the main reasons for this relate to the intra-class discrepancy between face images in different poses and the pose imbalances of training datasets. Learning pose-robust features by traversing to the feature space of frontal faces provides an effective and cheap way to alleviate this problem. In this paper, we present a method for progressively transforming profile face representations to the canonical pose with an attentive pair-wise loss. Firstly, to reduce the difficulty of directly transforming the profile face features into a frontal pose, we propose to learn the feature residual between the source pose and its nearby pose in a block-byblock fashion, and thus traversing to the feature space of a smaller pose by adding the learned residual. Secondly, we propose an attentive pair-wise loss to guide the feature transformation progressing in the most effective direction. Finally, our proposed progressive module and attentive pair-wise loss are light-weight and easy to implement, adding only about 7:5% extra parameters. Evaluations on the CFP and CPLFW datasets demonstrate the superiority of our proposed method. Code is available at https://github.com/hjy1312/AGPM.