Multilabel Remote Sensing Image Retrieval Based on Fully Convolutional Network
Conventional remote sensing image retrieval (RSIR) system usually performs single-label retrieval where each image is annotated by a single label representing the most significant semantic content of the image. In this scenario, however, the scene complexity of remote sensing images is ignored, wher...
Main Authors: | Zhenfeng Shao, Weixun Zhou, Xueqing Deng, Maoding Zhang, Qimin Cheng |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8954885/ |
Similar Items
-
A Benchmark Dataset for Performance Evaluation of Multi-Label Remote Sensing Image Retrieval
by: Zhenfeng Shao, et al.
Published: (2018-06-01) -
Evolutionary Multilabel Classification Algorithm Based on Cultural Algorithm
by: Qinghua Wu, et al.
Published: (2021-02-01) -
Multilabel Remote Sensing Image Annotation With Multiscale Attention and Label Correlation
by: Rui Huang, et al.
Published: (2021-01-01) -
Coarse-to-Fine Deep Metric Learning for Remote Sensing Image Retrieval
by: Min-Sub Yun, et al.
Published: (2020-01-01) -
A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image Retrieval
by: Famao Ye, et al.
Published: (2019-01-01)