Abstract
For unsupervised data-dependent hashing, the two most important requirements are to preserve similarity in the low-dimensional feature space and to minimize the binary quantization loss. A well-established hashing approach is Iterative Quantization (ITQ), which addresses these two requirements in separate steps. In this paper, we revisit the ITQ approach and propose novel formulations and algorithms to the problem. Specifically, we propose a novel approach, named Simultaneous Compression and Quantization (SCQ), to jointly learn to compress (reduce dimensionality) and binarize input data in a single formulation under strict orthogonal constraint. With this approach, we introduce a loss function and its relaxed version, termed Orthonormal Encoder (OnE) and Orthogonal Encoder (OgE) respectively, which involve challenging binary and orthogonal constraints. We propose to attack the optimization using novel algorithms based on recent advances in cyclic coordinate descent approach. Comprehensive experiments on unsupervised image retrieval demonstrate that our proposed methods consistently outperform other state-of-the-art hashing methods. Notably, our proposed methods outperform recent deep neural networks and GAN based hashing in accuracy, while being very computationally-efficient.
Abstract (translated)
对于无监督的数据相关散列，两个最重要的要求是保持低维特征空间中的相似性并最小化二进制量化损失。一种成熟的散列方法是迭代量化（ITQ），它在不同的步骤中解决了这两个要求。在本文中，我们重新审视了ITQ方法，并针对该问题提出了新颖的公式和算法。具体而言，我们提出了一种新的方法，称为同时压缩和量化（SCQ），共同学习在严格的正交约束下压缩（降低维数）和在单个配方中二值化输入数据。通过这种方法，我们分别引入了损失函数及其松弛版本，分别称为正交编码器（OnE）和正交编码器（OgE），其涉及挑战二进制和正交约束。我们建议使用基于循环坐标下降方法的最新进展的新算法来攻击优化。无监督图像检索的综合实验表明，我们提出的方法始终优于其他最先进的散列方法。值得注意的是，我们提出的方法在精度上优于最近的深度神经网络和基于GAN的散列，同时计算效率非常高。
URL
https://arxiv.org/abs/1802.06645
