一个模块同时生成多种长度哈希码，提升图像检索效率与效果。
Nested Hash Layer: A Plug-and-play Module for Multiple-length Hash Code Learning
- 通过嵌套结构一次性生成多长度哈希码，无需重复训练。
- 相比单长度模型，平均性能提升3.4%，训练速度提高5至8倍。
- 适合需要快速适配不同哈希长度的图像检索系统。
深度监督哈希对大规模图像检索中的高效存储与搜索至关重要。传统方法仅生成单一长度的哈希码，导致效率与效果间存在权衡；为找到最优长度需训练多个模型，显著增加时间和计算开销。此外，不同长度哈希码之间的关系常被忽视。为此，我们提出嵌套哈希层（Nested Hash Layer, NHL），一种可即插即用的模块，能在同一模型中以嵌套结构同时生成多长度哈希码。为解决多目标优化中的梯度冲突，引入主导性感知动态加权策略调节梯度。进一步提出长-短级联自蒸馏方法，利用长哈希码指导短哈希码学习，提升整体编码质量。实验表明，NHL在多种深度监督哈希模型上实现约5至8倍的训练速度提升，平均性能提升约3.4%。
原文摘要 · Abstract (English)
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%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。