期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 4, 页码 3420-3443出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3007533
关键词
Image retrieval; Feature extraction; Learning systems; Remote sensing; Task analysis; Quantization (signal); Benchmark testing; Adversarial hash learning model (AHLM); content-based remote sensing image retrieval (CBRSIR); deep feature learning model (DFLM); hash learning
类别
资金
- National Natural Science Foundation of China [61801351, 61802190, 61772400]
- Key Laboratory of National Defense Science and Technology Foundation Project [6142113180302]
- China Postdoctoral Science Foundation [2017M620441]
- Xidian University New Teacher Innovation Fund Project [XJS18032]
- Xidian University Artificial Intelligence School Innovation Fund Project [YJS2028]
This article proposes a new content-based remote sensing image retrieval method, which combines a deep feature learning model and an adversarial hash learning model, to improve retrieval efficiency in large-scale CBRSIR tasks and achieve competitive performance.
The content-based remote sensing image retrieval (CBRSIR) has attracted increasing attention with the number of remote sensing (RS) images growing explosively. Benefiting from the strong capacity of the deep convolutional neural network (DCNN), the performance of CBRSIR has been improved in recent years. Although great successes have been obtained, learning the RS images representative features and enhancing the retrieval efficiency for the large-scale CBRSIR tasks are still two challenging problems. In this article, we propose a new CBRSIR method named feature and hash (FAH) learning, which consists of a deep feature learning model (DFLM) and an adversarial hash learning model (AHLM). The DFLM aims at learning the RS images; dense features to guarantee the retrieval precision. In the DFLM, the DCNN and the proposed feature aggregation are integrated to capture the multiscale features. Then, the discrimination of the obtained features can be highlighted by the attention map in the developed attention branch. The AHLM maps the dense features onto the compact hash codes so that the retrieval efficiency can be improved. The AHLM contains a hash learning submodel and an adversarial regularization submodel. In particular, the hash learning submodel learns the real-valued hash codes that are similarity preserved by semantic supervisions. The adversarial regularization submodel regularizes the real-valued hash codes to learn the discrete uniform distribution with possible values 0 and 1. In this way, the hash codes are coding-balanced and the quantization errors are reduced. Encouraging experimental results counted on three public benchmark data sets demonstrate that our FAH can achieve competitive performance in the CBRSIR task compared with many existing hash learning methods.
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