# TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security

arXiv: https://arxiv.org/abs/2308.10133 · HTML: https://mlsanity.com/paper/2308.10133/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 95 references that are in the map.
- First posted on arXiv 20 Aug 2023.

## Builds on (most cited first, 30 of 46)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [Persistence Images: A Stable Vector Representation of Persistent Homology](https://mlsanity.com/paper/1507.06217/) (2015)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Rethinking and Improving Relative Position Encoding for Vision Transformer](https://mlsanity.com/paper/2107.14222/) (2021)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)
- [MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers](https://mlsanity.com/paper/2305.07185/) (2023)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [All Tokens Matter: Token Labeling for Training Better Vision Transformers](https://mlsanity.com/paper/2104.10858/) (2021)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [InstaHide: Instance-hiding Schemes for Private Distributed Learning](https://mlsanity.com/paper/2010.02772/) (2020)
- [TransMix: Attend to Mix for Vision Transformers](https://mlsanity.com/paper/2111.09833/) (2021)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)

## Built on by (most cited first, 22 of 22)

- [Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection](https://mlsanity.com/paper/2409.02664/) (2024)
- [Privacy-Preserving Face Recognition Using Trainable Feature Subtraction](https://mlsanity.com/paper/2403.12457/) (2024)
- [FRoundation: Are Foundation Models Ready for Face Recognition?](https://mlsanity.com/paper/2410.23831/) (2024)
- [LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition](https://mlsanity.com/paper/2403.08161/) (2024)
- [TopoFR: A Closer Look at Topology Alignment on Face Recognition](https://mlsanity.com/paper/2410.10587/) (2024)
- [LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition](https://mlsanity.com/paper/2501.13420/) (2025)
- [AdaDistill: Adaptive Knowledge Distillation for Deep Face Recognition](https://mlsanity.com/paper/2407.01332/) (2024)
- [Identity Overlap Between Face Recognition Train/Test Data: Causing Optimistic Bias in Accuracy Measurement](https://mlsanity.com/paper/2405.09403/) (2024)
- [Survey and Taxonomy: The Role of Data-Centric AI in Transformer-Based Time Series Forecasting](https://mlsanity.com/paper/2407.19784/) (2024)
- [FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device](https://mlsanity.com/paper/2506.10361/) (2025)
- [FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition](https://mlsanity.com/paper/2604.09127/) (2026)
- [FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization](https://mlsanity.com/paper/2410.12312/) (2024)
- [OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations](https://mlsanity.com/paper/2412.02479/) (2024)
- [AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation](https://mlsanity.com/paper/2404.09555/) (2024)
- [Boosting Unconstrained Face Recognition with Targeted Style Adversary](https://mlsanity.com/paper/2408.07642/) (2024)
- [Local and Global Feature Attention Fusion Network for Face Recognition](https://mlsanity.com/paper/2411.16169/) (2024)
- [Exploring Disparity-Accuracy Trade-offs in Face Recognition Systems: The Role of Datasets, Architectures, and Loss Functions](https://mlsanity.com/paper/2503.14138/) (2025)
- [Archival Faces: Detection of Faces in Digitized Historical Documents](https://mlsanity.com/paper/2504.00558/) (2025)
- [Boosting Adversarial Transferability Against Defenses via Multi-Scale Transformation](https://mlsanity.com/paper/2507.01791/) (2025)
- [EventFace: Event-Based Face Recognition via Structure-Driven Spatiotemporal Modeling](https://mlsanity.com/paper/2604.06782/) (2026)
- [Vision Transformers for Face Recognition Need More Registers](https://mlsanity.com/paper/2606.12036/) (2026)
- [Towards Robust Classroom Attendance: A Comprehensive Evaluation of Face Detection and Recognition Models](https://mlsanity.com/paper/2609.22750/) (2026)

## Abstract (arXiv)

Face Recognition (FR) technology has made significant strides with the emergence of deep learning. Typically, most existing FR models are built upon Convolutional Neural Networks (CNN) and take RGB face images as the model's input. In this work, we take a closer look at existing FR paradigms from high-efficiency, security, and precision perspectives, and identify the following three problems: (i) CNN frameworks are vulnerable in capturing global facial features and modeling the correlations between local facial features. (ii) Selecting RGB face images as the model's input greatly degrades the model's inference efficiency, increasing the extra computation costs. (iii) In the real-world FR system that operates on RGB face images, the integrity of user privacy may be compromised if hackers successfully penetrate and gain access to the input of this model. To solve these three issues, we propose two novel FR frameworks, i.e., TransFace and TransFace++, which successfully explore the feasibility of applying ViTs and image bytes to FR tasks, respectively. Experiments on popular face benchmarks demonstrate the superiority of our TransFace and TransFace++. Code is available at https://github.com/DanJun6737/TransFace_pp.