抗碰撞的单次传递方法用于无监督细粒度图像哈希
Collision-Resistant Single-Pass Method for Unsupervised Fine-Grained Image Hashing
AI总结:
本文提出了一种抗碰撞的单次传递自监督语义哈希方法(CS3H),通过单次传递归一化汉明距离损失直接优化汉明空间相似性,生成良好的二进制表示,同时引入了对碰撞敏感的注意力模块以强调稀有且判别性的局部模式,从而减少哈希碰撞并提高细粒度判别能力。
摘要:
无监督细粒度图像哈希旨在学习紧凑的二进制代码,以在高度相似实例之间保留细微的视觉差异,而无需人工标注。然而,大多数现有方法忽视了碰撞抵抗性,导致略微语义不同的样本具有相同的哈希代码。在本文中,我们提出了一种抗碰撞的单次传递自监督语义哈希(CS3H)框架,该框架通过单次传递归一化汉明距离损失直接优化汉明空间相似性,以生成良好的二进制表示。我们进一步引入了对碰撞敏感的注意力模块,以强调稀有且判别性的局部模式,从而减少哈希碰撞并提高细粒度判别能力。在多个基准测试中,实验表明CS3H在检索准确性上始终优于最先进的方法,同时在最小计算开销的情况下实现了优越的碰撞抵抗性。
英文摘要:
Unsupervised fine-grained image hashing aims to learn compact binary codes that preserve subtle visual differences among highly similar instances without manual annotations. However, most existing methods neglect collision resistance, leading to identical hash codes for slightly semantically different samples. In this paper, we propose Collision-Resistant Single-Pass Self-Supervised Semantic Hashing (CS3H), a collision-resistant framework that directly optimizes Hamming-space similarity via a single-pass normalized Hamming distance loss to produce well-separated binary representations. We further introduce a collision-sensitive attention module to emphasize rare and discriminative local patterns, reducing hash collisions and improving fine-grained discrimination. Experiments on multiple benchmarks show that CS3H consistently outperforms state-of-the-art methods in retrieval accuracy while achieving superior collision resistance with minimal computational overhead.
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。