# FRoundation: Are Foundation Models Ready for Face Recognition?

arXiv: https://arxiv.org/abs/2410.23831 · HTML: https://mlsanity.com/paper/2410.23831/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 75 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Builds on (most cited first, 30 of 55)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [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)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [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)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA](https://mlsanity.com/paper/2312.03732/) (2023)

## Built on by (most cited first, 23 of 23)

- [FaceXBench: Evaluating Multimodal LLMs on Face Understanding](https://mlsanity.com/paper/2501.10360/) (2025)
- [50 Years of Automated Face Recognition](https://mlsanity.com/paper/2505.24247/) (2025)
- [FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection](https://mlsanity.com/paper/2501.02892/) (2025)
- [MADation: Face Morphing Attack Detection with Foundation Models](https://mlsanity.com/paper/2501.03800/) (2025)
- [Benchmarking Foundation Models for Zero-Shot Biometric Tasks](https://mlsanity.com/paper/2505.24214/) (2025)
- [Foundation versus Domain-specific Models: Performance Comparison, Fusion, and Explainability in Face Recognition](https://mlsanity.com/paper/2507.03541/) (2025)
- [UniF2ace: A Unified Fine-grained Face Understanding and Generation Model](https://mlsanity.com/paper/2503.08120/) (2025)
- [ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers](https://mlsanity.com/paper/2601.05741/) (2026)
- [Can Foundation Models Generalise the Presentation Attack Detection Capabilities on ID Cards?](https://mlsanity.com/paper/2506.05263/) (2025)
- [MADPromptS: Unlocking Zero-Shot Morphing Attack Detection with Multiple Prompt Aggregation](https://mlsanity.com/paper/2508.08939/) (2025)
- [DiffProb: Data Pruning for Face Recognition](https://mlsanity.com/paper/2505.15272/) (2025)
- [Can Foundation Models Predict Fitness for Duty?](https://mlsanity.com/paper/2507.20418/) (2025)
- [Trade-offs in Cross-Domain Generalization of Foundation Model Fine-Tuned for Biometric Applications](https://mlsanity.com/paper/2509.14921/) (2025)
- [Face, Whole-Person, and Object Classification in a Unified Space Via The Interleaved Multi-Domain Identity Curriculum](https://mlsanity.com/paper/2511.19846/) (2025)
- [Mitigating Bias with Words: Inducing Demographic Ambiguity in Face Recognition Templates by Text Encoding](https://mlsanity.com/paper/2512.08981/) (2025)
- [EX-FIQA: Leveraging Intermediate Early eXit Representations from Vision Transformers for Face Image Quality Assessment](https://mlsanity.com/paper/2604.22842/) (2026)
- [ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation](https://mlsanity.com/paper/2606.12023/) (2026)
- [Vision Transformers for Face Recognition Need More Registers](https://mlsanity.com/paper/2606.12036/) (2026)
- [Causal Supervision of Attention for Affective Behaviour Analysis](https://mlsanity.com/paper/2607.12091/) (2026)
- [ReCowGnition: A Realistic Biometric Benchmark for Cow Face Recognition](https://mlsanity.com/paper/2607.22071/) (2026)
- [IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data](https://mlsanity.com/paper/2607.24422/) (2026)
- [Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection](https://mlsanity.com/paper/2608.29802/) (2026)
- [Learning Steadily: Accumulating Relative Point Margin Scores for Face Image Quality Assessment](https://mlsanity.com/paper/2609.31662/) (2026)

## Abstract (arXiv)

Foundation models are predominantly trained in an unsupervised or self-supervised manner on highly diverse and large-scale datasets, making them broadly applicable to various downstream tasks. In this work, we investigate for the first time whether such models are suitable for the specific domain of face recognition (FR). We further propose and demonstrate the adaptation of these models for FR across different levels of data availability, including synthetic data. Extensive experiments are conducted on multiple foundation models and datasets of varying scales for training and fine-tuning, with evaluation on a wide range of benchmarks. Our results indicate that, despite their versatility, pre-trained foundation models tend to underperform in FR in comparison with similar architectures trained specifically for this task. However, fine-tuning foundation models yields promising results, often surpassing models trained from scratch, particularly when training data is limited. For example, after fine-tuning only on 1K identities, DINOv2 ViT-S achieved average verification accuracy on LFW, CALFW, CPLFW, CFP-FP, and AgeDB30 benchmarks of 87.10%, compared to 64.70% achieved by the same model and without fine-tuning. While training the same model architecture, ViT-S, from scratch on 1k identities reached 69.96%. With access to larger-scale FR training datasets, these performances reach 96.03% and 95.59% for the DINOv2 and CLIP ViT-L models, respectively. In comparison to the ViT-based architectures trained from scratch for FR, fine-tuned same architectures of foundation models achieve similar performance while requiring lower training computational costs and not relying on the assumption of extensive data availability. We further demonstrated the use of synthetic face data, showing improved performances over both pre-trained foundation and ViT models.