Abstract
Recognizability, a key perceptual factor in human face processing, strongly affects the performance of face recognition (FR) systems in both verification and identification tasks. Effectively using recognizability to enhance feature representation remains challenging. In deep FR, the loss function plays a crucial role in shaping how features are embedded. However, current methods have two main drawbacks: (i) recognizability is only partially captured through soft margin constraints, resulting in weaker quality representation and lower discrimination, especially for low-quality or ambiguous faces; (ii) mutual overlapping gradients between feature direction and magnitude introduce undesirable interactions during optimization, causing instability and confusion in hypersphere planning, which may result in poor generalization, and entangled representations where recognizability and identity are not cleanly separated. To address these issues, we introduce a hard margin strategy - Quality Control Face (QCFace), which overcomes the mutual overlapping gradient problem and enables the clear decoupling of recognizability from identity representation. Based on this strategy, a novel hard-margin-based loss function employs a guidance factor for hypersphere planning, simultaneously optimizing for recognition ability and explicit recognizability representation. Extensive experiments confirm that QCFace not only provides robust and quantifiable recognizability encoding but also achieves state-of-the-art performance in both verification and identification benchmarks compared to existing recognizability-based losses.
Abstract (translated)
可识别性是人类面部处理中的一个关键感知因素，它强烈影响着人脸验证和识别任务中人脸识别（FR）系统的性能。有效利用可识别性来增强特征表示仍然是一个挑战。在深度人脸识别中，损失函数在塑造特征如何嵌入方面起着至关重要的作用。然而，当前的方法存在两个主要缺点：(i) 可识别性仅通过软边距约束部分捕获，导致质量较低的表示和区分度较差，特别是在处理低质量和模糊人脸时；(ii) 特征方向与幅度之间的相互重叠梯度在优化过程中引入了不希望看到的交互作用，这可能导致泛化能力差，并且可识别性和身份特征纠缠不清。为了解决这些问题，我们提出了一种硬边距策略——质量控制面部（QCFace），该方法克服了相互重叠梯度的问题，并使得可识别性与身份表示能够清晰分离。基于这一策略，一种新的以硬边距为基础的损失函数采用了一个用于超球体规划的引导因子，同时优化识别人脸的能力和明确的可识别性表示。广泛的实验确认QCFace不仅提供了稳健且量化的可识别性编码，而且在验证和识别基准测试中相对于现有的基于可识别性的损失方法实现了最先进的性能。
URL
https://arxiv.org/abs/2510.15289
