用CLIP单次微调实现低误报率人脸识别，无需海量特征提取。
CLIP Unreasonable Potential in Single-Shot Face Recognition
- 利用CLIP的图文对齐能力，结合单次微调提升识别性能。
- 部署后误报率降低，无需大规模特征采集与训练。
- 适合追求轻量化、高泛化的人脸识别场景应用。
人脸识别是计算机视觉的核心任务，通过分析面部模式和特征来识别与认证个体，广泛应用于安全认证和个人化场景。传统方法聚焦于捕捉眼睛、鼻子、嘴巴等面部特征，并与数据库匹配以验证身份，但因个体间特征相似性，高误报率问题长期存在。近期，OpenAI提出的对比语言图像预训练（CLIP）模型通过融合自然语言处理与视觉任务，展现出跨模态泛化能力。本文利用CLIP的视觉-语言关联特性，结合单次微调，在无需大规模面部特征提取的情况下，即可实现部署后更低的误报率。该方法证明了CLIP在解决人脸识别模型性能瓶颈方面的巨大潜力，且不改变现有训练范式。
原文摘要 · Abstract (English)
Face recognition is a core task in computer vision designed to identify and authenticate individuals by analyzing facial patterns and features. This field intersects with artificial intelligence image processing and machine learning with applications in security authentication and personalization. Traditional approaches in facial recognition focus on capturing facial features like the eyes, nose and mouth and matching these against a database to verify identities. However challenges such as high false positive rates have persisted often due to the similarity among individuals facial features. Recently Contrastive Language Image Pretraining (CLIP) a model developed by OpenAI has shown promising advancements by linking natural language processing with vision tasks allowing it to generalize across modalities. Using CLIP's vision language correspondence and single-shot finetuning the model can achieve lower false positive rates upon deployment without the need of mass facial features extraction. This integration demonstrating CLIP's potential to address persistent issues in face recognition model performance without complicating our training paradigm.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。