Abstract
Recently, deep metric learning techniques received attention, as the learned distance representations are useful to capture the similarity relationship among samples and further improve the performance of various of supervised or unsupervised learning tasks. We propose a novel supervised metric learning method that can learn the distance metrics in both geometric and probabilistic space for image recognition. In contrast to the previous metric learning methods which usually focus on learning the distance metrics in Euclidean space, our proposed method is able to learn better distance representation in a hybrid approach. To achieve this, we proposed a Generalized Hybrid Metric Loss (GHM-Loss) to learn the general hybrid proximity features from the image data by controlling the trade-off between geometric proximity and probabilistic proximity. To evaluate the effectiveness of our method, we first provide theoretical derivations and proofs of the proposed loss function, then we perform extensive experiments on two public datasets to show the advantage of our method compared to other state-of-the-art metric learning methods.
Abstract (translated)
最近,深度度量学习技术受到了关注,因为通过学习距离表示可以捕捉样本之间的相似关系并进一步提高监督或无监督学习任务的各种性能。我们提出了一种新的有监督度量学习方法,该方法可以在几何和概率空间中学习距离度量,用于图像识别。与以前的度量学习方法通常关注在欧氏空间中学习距离度量相反,我们提出的方法能够在混合方法中更好地学习距离表示。为了实现这一点,我们提出了一种 Generalized Hybrid Metric Loss (GHM-Loss),通过控制几何接近和概率接近之间的权衡来学习从图像数据中提取的一般混合接近特征。为了评估我们方法的效果,我们首先提供了提出的损失函数的理论推导和证明,然后对两个公开数据集进行广泛的实验,以展示我们方法相比其他先进的度量学习方法的优势。
URL
https://arxiv.org/abs/2301.13459