Abstract
Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The proposed method, termed as Density Aware Metric Learning, enforces the model to learn embeddings that are pulled towards the most dense region of the clusters for each class. It is achieved by iteratively shifting the estimate of the center towards the dense region of the cluster thereby leading to faster convergence and higher generalizability. In addition to this, the approach is robust to noisy samples in the training data, often present as outliers. Detailed experiments and analysis on two challenging cross-modal face recognition databases and two popular object recognition databases exhibit the efficacy of the proposed approach. It has superior convergence, requires lesser training time, and yields better accuracies than several popular deep metric learning methods.
Abstract (translated)
利用深度度量学习算法，学习了对未知类进行有效分类的判别和可推广模型。本文提出了一种新的抗噪声深度度量学习算法。该方法被称为密度感知度量学习，它强制模型学习嵌入，这些嵌入被拉向每个类的集群中最密集的区域。它是通过迭代将中心的估计值移到簇的密集区域来实现的，从而导致更快的收敛性和更高的可推广性。除此之外，该方法对训练数据中的噪声样本（通常以离群值的形式出现）具有鲁棒性。对两个具有挑战性的跨模态人脸识别数据库和两个流行的目标识别数据库进行了详细的实验和分析，证明了该方法的有效性。它具有优越的收敛性，需要较少的训练时间，并且比几种流行的深度度量学习方法获得更好的精度。
URL
https://arxiv.org/abs/1904.03911
