期刊
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
卷 23, 期 12, 页码 25236-25248出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2022.3213320
关键词
Cross-modal retrieval; manifold embedding; hash learning; balanced matrix
资金
- Guangxi Science and Technology [2019GXNSFFA245014, AD20159034]
- National Natural Science Foundation of China [62172120, 61936002]
- Guangxi Key Laboratory of Image and Graphic Intelligent Processing [GIIP2001]
This paper proposes a novel supervised hashing method, LGDH, which simultaneously preserves the comprehensive manifold structure and discriminative balanced codes in the Hamming space. By utilizing local category distribution and label-guided matrix construction, LGDH improves the discriminative power and balance of hash codes. Extensive experiments show that LGDH outperforms other methods in cross-modal tasks.
Due to their low storage capacity and fast retrieval speed, hashing techniques have received much attention in crossmodal retrieval. However, there are some issues that need to be further explored. First, some existing hashing methods use the labels to construct the semantic similarity matrix between pairwise data, ignoring the potential manifold structure between heterogeneous data. Second, some existing methods underestimate the importance of multi-label and the gaps between different class labels, making the learned hash codes less discriminative. Third, few of them embed both manifold and balanced structures within the same model, and the relaxation of discrete constraints will lead to an increasing quantization error. To mitigate these problems, this paper proposes a novel supervised hashing method, termed Label Guided Discrete Hashing (LGDH), which simultaneously preserves the comprehensive manifold structure and discriminative balanced codes that are both constructed by label information into Hamming space. We develop a local category distribution of the nearest neighbors, to excavate the underlying manifold structure of heterogeneous data. To maximize the gaps of different categories, a balanced matrix is constructed by labels to generate hash codes with balanced bits. For multi-label data, we also design a novel multi-label manifold and balanced structure matrix to adapt the real-world scenarios. An effective discrete optimization method is used to optimize our proposed objective function instead of the relaxation one. Extensive experiments on three benchmark datasets verify the effectiveness of LGDH. The comparison results demonstrat that LGDH achieves about 2% and 3% improved to different cross-modal tasks on average.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据