LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918125381877760 |
|---|---|
| author | You, Jinghan Li, Shanglin Sun, Yuanrui Wei, Jiangchuan Guo, Mingyu Feng, Chao Ran, Jiao |
| author_facet | You, Jinghan Li, Shanglin Sun, Yuanrui Wei, Jiangchuan Guo, Mingyu Feng, Chao Ran, Jiao |
| contents | Vision Transformers (ViTs) have revolutionized large-scale visual modeling, yet remain underexplored in face recognition (FR) where CNNs still dominate. We identify a critical bottleneck: CNN-inspired training paradigms fail to unlock ViT's potential, leading to suboptimal performance and convergence instability.To address this challenge, we propose LVFace, a ViT-based FR model that integrates Progressive Cluster Optimization (PCO) to achieve superior results. Specifically, PCO sequentially applies negative class sub-sampling (NCS) for robust and fast feature alignment from random initialization, feature expectation penalties for centroid stabilization, performing cluster boundary refinement through full-batch training without NCS constraints. LVFace establishes a new state-of-the-art face recognition baseline, surpassing leading approaches such as UniFace and TopoFR across multiple benchmarks. Extensive experiments demonstrate that LVFace delivers consistent performance gains, while exhibiting scalability to large-scale datasets and compatibility with mainstream VLMs and LLMs. Notably, LVFace secured 1st place in the ICCV 2021 Masked Face Recognition (MFR)-Ongoing Challenge (March 2025), proving its efficacy in real-world scenarios. Project is available at https://github.com/bytedance/LVFace. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13420 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition You, Jinghan Li, Shanglin Sun, Yuanrui Wei, Jiangchuan Guo, Mingyu Feng, Chao Ran, Jiao Computer Vision and Pattern Recognition Vision Transformers (ViTs) have revolutionized large-scale visual modeling, yet remain underexplored in face recognition (FR) where CNNs still dominate. We identify a critical bottleneck: CNN-inspired training paradigms fail to unlock ViT's potential, leading to suboptimal performance and convergence instability.To address this challenge, we propose LVFace, a ViT-based FR model that integrates Progressive Cluster Optimization (PCO) to achieve superior results. Specifically, PCO sequentially applies negative class sub-sampling (NCS) for robust and fast feature alignment from random initialization, feature expectation penalties for centroid stabilization, performing cluster boundary refinement through full-batch training without NCS constraints. LVFace establishes a new state-of-the-art face recognition baseline, surpassing leading approaches such as UniFace and TopoFR across multiple benchmarks. Extensive experiments demonstrate that LVFace delivers consistent performance gains, while exhibiting scalability to large-scale datasets and compatibility with mainstream VLMs and LLMs. Notably, LVFace secured 1st place in the ICCV 2021 Masked Face Recognition (MFR)-Ongoing Challenge (March 2025), proving its efficacy in real-world scenarios. Project is available at https://github.com/bytedance/LVFace. |
| title | LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.13420 |