Abstract
Representing images by compact hash codes is an attractive approach for large-scale content-based image retrieval. In most state-of-the-art hashing-based image retrieval systems, for each image, local descriptors are first aggregated as a global representation vector. This global vector is then subjected to a hashing function to generate a binary hash code. In previous works, the aggregating and the hashing processes are designed independently. Hence these frameworks may generate suboptimal hash codes. In this paper, we first propose a novel unsupervised hashing framework in which feature aggregating and hashing are designed simultaneously and optimized jointly. Specifically, our joint optimization generates aggregated representations that can be better reconstructed by some binary codes. This leads to more discriminative binary hash codes and improved retrieval accuracy. In addition, the proposed method is flexible. It can be extended for supervised hashing. When the data label is available, the framework can be adapted to learn binary codes which minimize the reconstruction loss w.r.t. label vectors. Furthermore, we also propose a fast version of the state-of-the-art hashing method Binary Autoencoder to be used in our proposed frameworks. Extensive experiments on benchmark datasets under various settings show that the proposed methods outperform state-of-the-art unsupervised and supervised hashing methods.
Abstract (translated)
用紧凑的散列码表示图像是一种有吸引力的大规模基于内容的图像检索方法。在大多数最先进的基于哈希的图像检索系统中，对于每个图像，本地描述符首先被聚合为全局表示向量。然后，这个全局向量接受哈希函数以生成二进制哈希代码。在前面的工作中，聚合和散列过程是独立设计的。因此，这些框架可能生成次优散列码。本文首先提出了一种新的无监督散列框架，该框架同时设计了特征聚合和散列，并对其进行了优化。具体来说，我们的联合优化生成聚合表示，可以更好地由一些二进制代码重构。这将导致更具识别性的二进制散列码和更高的检索精度。此外，该方法具有一定的灵活性。它可以扩展到监督哈希。当数据标签可用时，可以调整框架来学习二进制代码，以最小化重建损失w.r.t.标签向量。此外，我们还提出了一个快速版本的最先进的散列方法二进制自动编码器，将在我们提出的框架中使用。在各种设置下对基准数据集进行的大量实验表明，所提出的方法优于最先进的无监督和监督哈希方法。
URL
https://arxiv.org/abs/1904.11820
