论文标题
哈希代码性能的下限
A Lower Bound of Hash Codes' Performance
论文作者
论文摘要
作为紧凑型表示学习的关键方法，哈希在有效性和效率上取得了巨大的成功。许多启发式锤式空间度量学习目标旨在获得高质量的哈希守则。然而，对学习良好哈希守则的标准的理论分析在很大程度上尚未得到解释。在本文中，我们证明了哈希码之间的类间独特性和类内的紧凑性决定了哈希码的性能的下限。促进这两个特征可以提高界限并改善哈希学习。然后，我们提出了一个替代模型，以通过估计哈希码的后验并控制它来充分利用上述目标，从而导致低偏差优化。广泛的实验揭示了所提出的方法的有效性。通过对一系列哈希模型进行测试，我们可以在所有这些中获得性能提高，平均平均精度最高为$ 26.5 \％$ $，准确性提高了$ 20.5 \％$。我们的代码可在https://github.com/vl-group/lbhash上公开获取。
As a crucial approach for compact representation learning, hashing has achieved great success in effectiveness and efficiency. Numerous heuristic Hamming space metric learning objectives are designed to obtain high-quality hash codes. Nevertheless, a theoretical analysis of criteria for learning good hash codes remains largely unexploited. In this paper, we prove that inter-class distinctiveness and intra-class compactness among hash codes determine the lower bound of hash codes' performance. Promoting these two characteristics could lift the bound and improve hash learning. We then propose a surrogate model to fully exploit the above objective by estimating the posterior of hash codes and controlling it, which results in a low-bias optimization. Extensive experiments reveal the effectiveness of the proposed method. By testing on a series of hash-models, we obtain performance improvements among all of them, with an up to $26.5\%$ increase in mean Average Precision and an up to $20.5\%$ increase in accuracy. Our code is publicly available at https://github.com/VL-Group/LBHash.
