Nested Hash Layer：一种用于多长度哈希码学习的即插即用模块
Nested Hash Layer: A Plug-and-play Module for Multiple-length Hash Code Learning
AI总结：
提出即插即用模块NHL，通过嵌套结构同时生成多长度哈希码，结合动态加权与自蒸馏策略优化训练，在多模型上实现5至8倍加速并提升约3.4%性能。
摘要：
深度监督哈希对于大规模图像检索中的高效存储和搜索至关重要。传统的深度监督哈希模型生成单一长度的哈希码，但这在不同码长下造成了效率与有效性之间的权衡。为了寻找任务的最优长度，必须训练多个模型，增加了时间和计算开销。此外，不同长度哈希码之间的关系常被忽略。为解决这些问题，我们提出了Nested Hash Layer（NHL），一种用于深度监督哈希模型的即插即用模块。NHL以嵌套结构同时生成多种长度的哈希码。为解决多学习目标带来的优化冲突，我们引入了一种主导感知的动态加权策略来调整梯度。此外，我们提出了一种长短级联自蒸馏方法，其中长哈希码指导较短哈希码的学习，从而提升整体码质量。实验表明，NHL在各种深度监督哈希模型中实现了约5至8倍的总体训练速度提升，并将这些模型的平均性能提高了约3.4%。
英文摘要：
Deep supervised hashing is essential for efficient storage and search in large-scale image retrieval. Traditional deep supervised hashing models generate single-length hash codes, but this creates a trade-off between efficiency and effectiveness for different code lengths. To find the optimal length for a task, multiple models must be trained, increasing time and computation. Furthermore, relationships between hash codes of different lengths are often ignored. To address these issues, we propose the Nested Hash Layer (NHL), a plug-and-play module for deep supervised hashing models. NHL generates hash codes of multiple lengths simultaneously in a nested structure. To resolve optimization conflicts from multiple learning objectives, we introduce a dominance-aware dynamic weighting strategy to adjust gradients. Additionally, we propose a long-short cascade self-distillation method, where long hash codes guide the learning of shorter ones, improving overall code quality. Experiments indicate that the NHL achieves an overall training speed improvement of approximately 5 to 8 times across various deep supervised hashing models and enhances the average performance of these models by about 3.4%.
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。
