TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security
This work addresses efficiency and security issues in face recognition systems, offering a novel approach that could impact real-world applications, though it appears incremental by building on existing ViT and byte-based methods.
The paper tackled problems in face recognition (FR) related to accuracy, efficiency, and security by proposing TransFace and TransFace++ frameworks, which use Vision Transformers (ViTs) and image bytes to achieve state-of-the-art results on benchmarks.
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.