期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 30, 期 -, 页码 332-344出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2020.3036735
关键词
Binary codes; Training; Semantics; Generators; Image retrieval; Hash functions; Visualization; Scalable image search; fast similarity search; hashing; deep learning; multi-label learning
资金
- National Key Research and Development Program of China [2020AAA0105200]
- National Natural Science Foundation of China [61822603, U1813218, 61672306]
- Beijing Academy of Artificial Intelligence (BAAI) [BAAI2020ZJ0202]
- Shenzhen Fundamental Research Fund (Subject Arrangement) [JCYJ20170412170602564]
- Institute for Guo Qiang, Tsinghua University
This paper proposes an adversarial multi-label variational hashing method to learn compact binary codes for efficient image retrieval. The method learns hash functions from both synthetic and real data, making it effective for unseen data. By simultaneously enforcing adversarial learning, discriminative binary codes learning, and generating synthetic training samples, the method demonstrates efficacy on benchmark datasets.
In this paper, we propose an adversarial multi-label variational hashing (AMVH) method to learn compact binary codes for efficient image retrieval. Unlike most existing deep hashing methods which only learn binary codes from specific real samples, our AMVH learns hash functions from both synthetic and real data which make our model effective for unseen data. Specifically, we design an end-to-end deep hashing framework which consists of a generator network and a discriminator-hashing network by enforcing simultaneous adversarial learning and discriminative binary codes learning to learn compact binary codes. The discriminator-hashing network learns binary codes by optimizing a multi-label discriminative criterion and minimizing the quantization loss between binary codes and real-value codes. The generator network is learned so that latent representations can be sampled in a probabilistic manner and used to generate new synthetic training sample for the discriminator-hashing network. Experimental results on several benchmark datasets show the efficacy of the proposed approach.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据