# Searching for Alignment in Face Recognition

arXiv: https://arxiv.org/abs/2102.05447 · HTML: https://mlsanity.com/paper/2102.05447/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 10 Feb 2021.

## Builds on (most cited first, 29 of 29)

- [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)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search](https://mlsanity.com/paper/1907.01845/) (2019)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [Faster AutoAugment: Learning Augmentation Strategies using Backpropagation](https://mlsanity.com/paper/1911.06987/) (2019)
- [DetNAS: Backbone Search for Object Detection](https://mlsanity.com/paper/1903.10979/) (2019)
- [Learning Meta Face Recognition in Unseen Domains](https://mlsanity.com/paper/2003.07733/) (2020)
- [Deeply learned face representations are sparse, selective, and robust](https://mlsanity.com/paper/1412.1265/) (2014)
- [Targeting Ultimate Accuracy: Face Recognition via Deep Embedding](https://mlsanity.com/paper/1506.07310/) (2015)
- [Face Synthesis for Eyeglass-Robust Face Recognition](https://mlsanity.com/paper/1806.01196/) (2018)
- [Large-scale Bisample Learning on ID Versus Spot Face Recognition](https://mlsanity.com/paper/1806.03018/) (2018)
- [Attentional Feature-Pair Relation Networks for Accurate Face Recognition](https://mlsanity.com/paper/1908.06255/) (2019)
- [GridFace: Face Rectification via Learning Local Homography Transformations](https://mlsanity.com/paper/1808.06210/) (2018)

## Built on by (most cited first, 12 of 12)

- [Learning Compatible Embeddings](https://mlsanity.com/paper/2108.01958/) (2021)
- [Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters](https://mlsanity.com/paper/2201.12467/) (2022)
- [PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition](https://mlsanity.com/paper/2107.11721/) (2021)
- [GaitFormer: Learning Gait Representations with Noisy Multi-Task Learning](https://mlsanity.com/paper/2310.19418/) (2023)
- [ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition](https://mlsanity.com/paper/2407.14972/) (2024)
- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [Towards Privacy-Preserving, Real-Time and Lossless Feature Matching](https://mlsanity.com/paper/2208.00214/) (2022)
- [Basket-based Softmax](https://mlsanity.com/paper/2201.09308/) (2022)
- [Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment](https://mlsanity.com/paper/2503.22359/) (2025)
- [Adaptive Discriminative Regularization for Visual Classification](https://mlsanity.com/paper/2203.00833/) (2022)
- [Robust Boosting Forests with Richer Deep Feature Hierarchy](https://mlsanity.com/paper/2210.16451/) (2022)
- [Generalization Limits in Vehicle Re-Identification](https://mlsanity.com/paper/2606.01981/) (2026)

## Abstract (arXiv)

A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing. Among them, face detection, landmark detection and representation learning have long been studied and a lot of works have been proposed. As an essential step with a significant impact on recognition performance, the alignment step has attracted little attention. In this paper, we first explore and highlight the effects of different alignment templates on face recognition. Then, for the first time, we try to search for the optimal template automatically. We construct a well-defined searching space by decomposing the template searching into the crop size and vertical shift, and propose an efficient method Face Alignment Policy Search (FAPS). Besides, a well-designed benchmark is proposed to evaluate the searched policy. Experiments on our proposed benchmark validate the effectiveness of our method to improve face recognition performance.