AI RESEARCH
Collision-Resistant Single-Pass Method for Unsupervised Fine-Grained Image Hashing
arXiv CS.CV
•
ArXi:2605.18288v1 Announce Type: new 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.