arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.07804cs.CV
收藏

CIMON:迈向高质量的Hash码

CIMON: Towards High-quality Hash Codes

Peking University(北京大学);Alibaba Group(阿里巴巴集团);Harbin Institute of Technology(哈尔滨工业大学)

Xiao Luo, Daqing Wu, Zeyu Ma, Chong Chen, Minghua Deng, Jinwen Ma, Zhongming Jin, Jianqiang Huang, Xian-Sheng Hua

摘要:

最近,散列算法因其存储和计算效率而被广泛应用于近似最近邻搜索。大多数无监督哈希方法通过从预训练模型构建局部语义相似性结构作为指导信息来学习将图像映射到语义相似性保持哈希码,即,如果每个点对在特征空间中的距离很小,则将它们相似地对待。然而,由于预训练模型的低效表示能力,在散列码学习过程中会引入许多局部语义相似度的假阳性和假阴性,并导致错误传播。而且,这些方法很少考虑模型的鲁棒性,这将导致哈希码对干扰的不稳定性。本文提出了一种新的方法-{ \textbf{C} }完全的{ \textbf{I} }相似性{\textbf{M} }的挖掘和{ \textbf{O} }完全的{ \textbf{N} }挖掘(CIMON)。首先,我们使用全局细化和相似性统计分布,以获得可靠和平滑的指导。其次,语义和对比一致性学习的引入,以获得干扰不变和歧视性哈希码。在多个基准数据集上的实验表明,该方法在检索性能和鲁棒性方面都优于各种最先进的方法。

英文摘要:

Recently, hashing is widely used in approximate nearest neighbor search for its storage and computational efficiency. Most of the unsupervised hashing methods learn to map images into semantic similarity-preserving hash codes by constructing local semantic similarity structure from the pre-trained model as the guiding information, i.e., treating each point pair similar if their distance is small in feature space. However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning. Moreover, few of the methods consider the robustness of models, which will cause instability of hash codes to disturbance. In this paper, we propose a new method named {\textbf{C}}omprehensive s{\textbf{I}}milarity {\textbf{M}}ining and c{\textbf{O}}nsistency lear{\textbf{N}}ing (CIMON). First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes. Extensive experiments on several benchmark datasets show that the proposed method outperforms a wide range of state-of-the-art methods in both retrieval performance and robustness.

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。

↑