| 摘要: |
| 由于具有低存储成本、高效检索、低标注成本等方面的优势，无监督的哈希技术已经引起了学术界越来越多的关注，并且已经广泛地应用到大规模数据库检索问题中.先前的无监督方法大部分依靠数据集本身的语义结构作为指导信息，要求在哈希空间中，数据的语义信息能够得到保持，从而完成哈希编码的学习.因此，如何精确地表示语义结构以及哈希编码成为了无监督哈希方法成功的关键.提出一种新的基于自监督学习的策略进行无监督哈希编码学习.具体来讲，首先利用对比学习在目标数据集上对网络进行学习，从而能够构建准确的语义相似性结构；接着，提出一个新的目标损失函数，期望在哈希空间中，数据的局部语义相似性结构能够得到保持，同时，哈希编码的辨识力能够得到提升，提出的网络框架是端到端可训练的；最后，提出的算法在两个大规模图像检索数据集上进行了测试，大量的实验验证了所提出算法的有效性. |
| 关键词: 无监督哈希 对比学习 实例辨别 局部语义结构 |
| DOI：10.13328/j.cnki.jos.006178 |
| 分类号: |
| 基金项目:国家自然科学基金（61806044，U2001211，61932004，61732003）；北京理工大学青年教师学术启动计划（3070012222010） |
|
| Local Semantic Structure Captured and Instance Discriminated by Unsupervised Hashing |
|
LI Chang-Sheng1, MIN Qi-Xing2, CHENG Yu-Rong1, YUAN Ye1, WANG Guo-Ren1
|
|
1.School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China;2.School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
|
| Abstract: |
| Recently, unsupervised Hashing has attracted much attention in the machine learning and information retrieval communities, due to its low storage and high search efficiency. Most of existing unsupervised Hashing methods rely on the local semantic structure of the data as the guiding information, requiring to preserve such semantic structure in the Hamming space. Thus, how to precisely represent the local structure of the data and Hashing code becomes the key point to success. This study proposes a novel Hashing method based on self-supervised learning. Specifically, it is proposed to utilize the contrast learning to acquire a compact and accurate feature representation for each sample, and then a semantic structure matrix can be constructed for representing the similarity between samples. Meanwhile, a new loss function is proposed to preserve the semantic information and improve the discriminative ability in the Hamming space, by the spirit of the instance discrimination method proposed recently. The proposed framework is end-to-end trainable. Extensive experiments on two large-scale image retrieval datasets show that the proposed method can significantly outperform current state-of-the-art methods. |
| Key words: unsupervised Hashing contrast learning instance discrimination local semantic structure |
