Abstract
With the growth of image on the web, research on hashing which enables high-speed image retrieval has been actively studied. In recent years, various hashing methods based on deep neural networks have been proposed and achieved higher precision than the other hashing methods. In these methods, multiple losses for hash codes and the parameters of neural networks are defined. They generate hash codes that minimize the weighted sum of the losses. Therefore, an expert has to tune the weights for the losses heuristically, and the probabilistic optimality of the loss function cannot be explained. In order to generate explainable hash codes without weight tuning, we theoretically derive a single loss function with no hyperparameters for the hash code from the probability distribution of the images. By generating hash codes that minimize this loss function, highly accurate image retrieval with probabilistic optimality is performed. We evaluate the performance of hashing using MNIST, CIFAR-10, SVHN and show that the proposed method outperforms the state-of-the-art hashing methods.
Abstract (translated)
随着网络上图像的不断增长,对支持高速图像检索的哈希算法的研究也越来越活跃。近年来,人们提出了各种基于深度神经网络的散列方法,并取得了比其它散列方法更高的精度。在这些方法中,定义了散列码的多重损失和神经网络的参数。它们生成散列码,使损失的加权和最小化。因此,专家必须以启发式的方式调整损失权重,而损失函数的概率最优性是无法解释的。为了在不进行权重调整的情况下生成可解释的散列码,我们从图像的概率分布出发,从理论上推导了散列码的一个无超参数的单损失函数。通过生成最小损失函数的散列码,实现了概率最优的高精度图像检索。我们使用mnist、cifar-10、svhn对散列的性能进行了评估,结果表明,该方法优于目前最先进的散列方法。
URL
https://arxiv.org/abs/1905.08501