Face verification can be regarded as a two-class fine-grained visual-recognition problem. Enhancing the feature’s discriminative power is one of the key problems to improve its performance. Metric-learning technology is often applied to address this need while achieving a good tradeoff between underfitting, and overfitting plays a vital role in metric learning. Hence, we propose a novel ensemble cascade metric-learning (ECML) mechanism. In particular, hierarchical metric learning is executed in a cascade way to alleviate underfitting. Meanwhile, at each learning level, the features are split into nonoverlapping groups. Then, metric learning is executed among the feature groups in the ensemble manner to resist overfitting. Considering the feature distribution characteristics of faces, a robust Mahalanobis metric-learning method (RMML) with a closed-form solution is additionally proposed. It can avoid the computation failure issue on an inverse matrix faced by some well-known metric-learning approaches (e.g., KISSME). Embedding RMML into the proposed ECML mechanism, our metric-learning paradigm (EC-RMML) can run in the one-pass learning manner. The experimental results demonstrate that EC-RMML is superior to state-of-the-art metric-learning methods for face verification. The proposed ECML mechanism is also applicable to other metric-learning approaches.

中文翻译：

---

ECML：面向人脸验证的集成级联度量学习机制


人脸验证可以被视为二类细粒度视觉识别问题。增强特征的判别力是提高其性能的关键问题之一。度量学习技术通常用于解决这一需求，同时在欠拟合和过拟合之间实现良好的权衡，在度量学习中发挥着至关重要的作用。因此，我们提出了一种新颖的集成级联度量学习（ECML）机制。特别是，分层度量学习以级联方式执行，以减轻欠拟合。同时，在每个学习级别，特征被分为不重叠的组。然后，以集成的方式在特征组之间执行度量学习以防止过度拟合。考虑到人脸的特征分布特征，还提出了一种具有封闭形式解决方案的鲁棒马哈拉诺比斯度量学习方法（RMML）。它可以避免一些众所周知的度量学习方法（例如，KISSME）面临的逆矩阵计算失败问题。将 RMML 嵌入到所提出的 ECML 机制中，我们的度量学习范式（EC-RMML）可以以一次性学习方式运行。实验结果表明，EC-RMML 优于最先进的人脸验证度量学习方法。所提出的 ECML 机制也适用于其他度量学习方法。