Asymmetric Supervised Fusion-Oriented Hashing for Cross-Modal Retrieval
Asymmetric Supervised Fusion-Oriented Hashing for Cross-Modal Retrieval
复制标题
DOI：
10.1109/tcyb.2023.3241018
复制
发表时间：
2023-02
影响因子：
11.8
通讯作者：
Zhan Yang;Xiyin Deng;Lin Guo;Jun Long
中科院分区：
文献类型：
--
作者：
Zhan Yang;Xiyin Deng;Lin Guo;Jun Long
哈希技术因其在搜索和存储任务中的优异性能而被广泛应用于大规模多模态检索任务。尽管已经提出了一些有效的散列方法，但仍然难以处理不同异构模态之间存在的内在联系。此外，通过基于松弛的策略优化离散约束问题会导致较大的量化误差并导致次优解。在本文中，我们提出了一种新颖的非对称监督融合哈希方法，名为（ASFOH），它研究了三种新颖的方案来解决上述问题。具体来说，我们首先将问题明确地表述为矩阵分解为公共潜在表示和变换矩阵，并结合自适应权重方案和核范数最小化，以确保多模态数据的信息完整性。然后，我们将公共潜在表示与语义标签矩阵相关联，从而通过构建非对称哈希学习框架来增加模型的判别能力，从而使生成的哈希码更加紧凑。最后，提出一种基于核范数最小化的高效离散优化迭代算法，将非凸多元优化问题分解为多个具有解析解的子问题。对 MIRFlirck、NUS-WIDE 和 IARP-TC12 数据集的综合实验证明，ASFOH 的性能优于最先进的方法。
Hashing technologies have been widely applied for large-scale multimodal retrieval tasks owing to their excellent performance in search and storage tasks. Although some effective hashing methods have been proposed, it is still difficult to handle the intrinsic linkages that exist among different heterogeneous modalities. Moreover, optimizing the discrete constraint problem through a relaxation-based strategy results in a large quantization error and leads to a suboptimal solution. In this article, we present a novel asymmetric supervised fusion-oriented hashing method, named (ASFOH), which investigates three novel schemes to remedy the above issues. Specifically, we first explicitly formulate the problem as matrix decomposition into a common latent representation and a transformation matrix, combined with an adaptive weight scheme and nuclear norm minimization to ensure the information completeness of multimodal data. Then, we associate the common latent representation with the semantic label matrix, thereby increasing the discriminative capability of the model by constructing an asymmetric hash learning framework, thus, making the generated hash codes more compact. Finally, an efficient discrete optimization iterative algorithm based on nuclear norm minimization is proposed to decompose the nonconvex multivariate optimization problem into several subproblems with analytical solutions. Comprehensive experiments on the MIRFlirck, NUS-WIDE, and IARP-TC12 datasets testify that ASFOH outperforms the compared state-of-the-art approaches.