Face recognition models often encounter various unseen domains and environments in real-world applications, leading to unsatisfactory performance due to the open-set nature of face recognition. Models trained on central datasets may exhibit poor generalization when faced with different candidates under varying illumination and blur conditions. In this paper, our goal is to enhance the generalization of face recognition models for diverse target conditions without relying on active or incremental learning. We propose an approach for face recognition that utilizes contrastive learning to synthesize positive and multiple negative samples. To address the combinatorial challenges posed by positive and negative samples, our framework incorporates a combination of contrastive regularizer loss and Arcface loss, along with an effective sampling strategy for batch model learning. We update the model weights by jointly back-propagating contrastive and ArcFace gradients. We validate our method on both generalized and standard face recognition benchmarks dataset namely IJB-B and IJB-C. Series of experimentation revealed the out-performance of proposed framework against other state-of-the-art methods.

中文翻译：

---

临时对比损失可改善开放环境中的人脸识别

人脸识别模型在现实应用中经常遇到各种看不见的领域和环境，由于人脸识别的开放集性质，导致性能不理想。当在不同的光照和模糊条件下面对不同的候选者时，在中心数据集上训练的模型可能表现出较差的泛化能力。在本文中，我们的目标是在不依赖主动或增量学习的情况下增强针对不同目标条件的人脸识别模型的泛化能力。我们提出了一种人脸识别方法，利用对比学习来合成正样本和多个负样本。为了解决正样本和负样本带来的组合挑战，我们的框架结合了对比正则化损失和 Arcface 损失，以及用于批量模型学习的有效采样策略。我们通过联合反向传播对比梯度和 ArcFace 梯度来更新模型权重。我们在通用和标准人脸识别基准数据集（即 IJB-B 和 IJB-C）上验证了我们的方法。一系列的实验揭示了所提出的框架相对于其他最先进的方法的性能。