哈希的互学习：从弱监督中解锁强哈希函数
Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision
AI总结：
针对深度哈希中基于中心方法忽视局部相似性的问题，提出互学习框架MLH，通过强弱分支互学习及哈希专家混合模块，在多个基准上超越现有方法。
摘要：
深度哈希已广泛应用于大规模图像检索，众多策略被提出以优化哈希函数学习。基于成对的方法在保留局部相似性关系方面有效，而基于中心的方法通常通过更有效地捕捉全局数据分布而获得更优性能。然而，基于中心的方法在建模全局结构方面的优势往往以未充分利用重要的局部相似性信息为代价。为解决这一局限，我们提出了哈希的互学习（MLH），一种新颖的从弱到强的框架，通过从较弱的基于成对的分支转移知识来增强基于中心的哈希分支。MLH包含两个分支：一个强的基于中心的分支和一个较弱的基于成对的分支。通过迭代的互学习过程，基于中心的分支利用由基于成对的分支学到的局部相似性线索。此外，受专家混合范式的启发，我们引入了一个新颖的哈希专家混合模块，该模块能够实现有效的跨分支交互，进一步提升两个分支的性能。大量实验表明，MLH在多个基准数据集上持续优于最先进的哈希方法。
英文摘要：
Deep hashing has been widely adopted for large-scale image retrieval, with numerous strategies proposed to optimize hash function learning. Pairwise-based methods are effective in learning hash functions that preserve local similarity relationships, whereas center-based methods typically achieve superior performance by more effectively capturing global data distributions. However, the strength of center-based methods in modeling global structures often comes at the expense of underutilizing important local similarity information. To address this limitation, we propose Mutual Learning for Hashing (MLH), a novel weak-to-strong framework that enhances a center-based hashing branch by transferring knowledge from a weaker pairwise-based branch. MLH consists of two branches: a strong center-based branch and a weaker pairwise-based branch. Through an iterative mutual learning process, the center-based branch leverages local similarity cues learned by the pairwise-based branch. Furthermore, inspired by the mixture-of-experts paradigm, we introduce a novel mixture-of-hash-experts module that enables effective cross-branch interaction, further enhancing the performance of both branches. Extensive experiments demonstrate that MLH consistently outperforms state-of-the-art hashing methods across multiple benchmark datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
