Collision-Resistant Single-Pass Method for Unsupervised Fine-Grained Image Hashing
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917508031709184 |
|---|---|
| author | Duong, Anh-Kiet Gomez-Krämer, Petra Carozza, Jean-Michel |
| author_facet | Duong, Anh-Kiet Gomez-Krämer, Petra Carozza, Jean-Michel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18288 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Collision-Resistant Single-Pass Method for Unsupervised Fine-Grained Image Hashing Duong, Anh-Kiet Gomez-Krämer, Petra Carozza, Jean-Michel Computer Vision and Pattern Recognition 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. |
| title | Collision-Resistant Single-Pass Method for Unsupervised Fine-Grained Image Hashing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.18288 |