提出一种无需标注的图像细粒度哈希方法，有效避免相似图像生成相同编码。
Collision-Resistant Single-Pass Method for Unsupervised Fine-Grained Image Hashing
- 单次遍历优化汉明距离损失，直接提升哈希码在空间中的区分度。
- 在多个数据集上检索准确率超越现有方法，且碰撞率显著降低。
- 适合需要高精度图像检索的场景，如细粒度分类与相似图搜索。
无监督细粒度图像哈希旨在学习紧凑的二进制编码，以保留高度相似样本间的细微视觉差异，而无需人工标注。然而，大多数现有方法忽视了碰撞抵抗性，导致语义略有不同的样本生成相同的哈希码。本文提出一种碰撞抵抗型单次遍历自监督语义哈希框架（CS3H），通过单次遍历的归一化汉明距离损失直接优化汉明空间相似性，生成分布更分散的二进制表示。我们进一步引入一种对碰撞敏感的注意力模块，强化稀有且具有判别性的局部模式，减少哈希碰撞，提升细粒度区分能力。在多个基准测试上的实验表明，CS3H在检索准确率上持续优于现有最先进方法，同时具备更优的碰撞抵抗性，且计算开销极低。
原文摘要 · Abstract (English)
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.
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。