.png){kind=icon}
.png){kind=icon}
返回
Learning Efficient Binary Codes From High-Level Feature Representations for Multilabel Image Retrieval
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2017.2703089.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Due to the efficiency and effectiveness of hashing technologies, they have become increasingly popular in large-scale image semantic retrieval. However, existing hash methods suppose that the data distributions satisfy the manifold assumption that semantic similar samples tend to lie on a low-dimensional manifold, which will be weakened due to the large intraclass variation. Moreover, these methods learn hash functions by relaxing the discrete constraints on binary codes to real value, which will introduce large quantization loss. To tackle the above problems, this paper proposes a novel unsupervised hashing algorithm to learn efficient binary codes from high-level feature representations. More specifically, we explore nonnegative matrix factorization for learning high-level visual features. Ultimately, binary codes are generated by performing binary quantization in the high-level feature representations space, which will map images with similar (visually or semantically) high-level feature representations to similar binary codes. To solve the corresponding optimization problem involving nonnegative and discrete variables, we develop an efficient optimization algorithm to reduce quantization loss with guaranteed convergence in theory. Extensive experiments show that our proposed method outperforms the state-of-the-art hashing methods on several multilabel real-world image datasets.
Keyword:
Efficient binary codes
image semantic retrieval
nonnegative matrix factorization
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。