.png){kind=icon}
返回
A Multiple-Instance Densely-Connected ConvNet for Aerial Scene Classification
.png){kind=icon}
OA
AI
DOI：10.1109/TIP.2020.2975718.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In contrast with nature scenes, aerial scenes are often composed of many objects crowdedly distributed on the surface in bird's view, the description of which usually demands more discriminative features as well as local semantics. However, when applied to scene classification, most of the existing convolution neural networks (ConvNets) tend to depict global semantics of images, and the loss of low- and mid-level features can hardly be avoided, especially when the model goes deeper. To tackle these challenges, in this paper, we propose a multiple-instance densely-connected ConvNet (MIDC-Net) for aerial scene classification. It regards aerial scene classification as a multiple-instance learning problem so that local semantics can be further investigated. Our classification model consists of an instance-level classifier, a multiple instance pooling and followed by a bag-level classification layer. In the instance-level classifier, we propose a simplified dense connection structure to effectively preserve features from different levels. The extracted convolution features are further converted into instance feature vectors. Then, we propose a trainable attention-based multiple instance pooling. It highlights the local semantics relevant to the scene label and outputs the bag-level probability directly. Finally, with our bag-level classification layer, this multiple instance learning framework is under the direct supervision of bag labels. Experiments on three widely-utilized aerial scene benchmarks demonstrate that our proposed method outperforms many state-of-the-art methods by a large margin with much fewer parameters.
Keyword:
Feature extraction
Semantics
Machine learning
Task analysis
Training
Neural networks
Visualization
Scene classification
convolutional neural network
multiple instance learning
dense connection
aerial image
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。
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
.png){kind=icon}
Large-Scale Weakly Supervised Object Localization via Latent Category Learning基于潜在类别学习的大规模弱监督目标定位
PREAI
分享收藏Depth-Aware Salient Object Detection and Segmentation via Multiscale Discriminative Saliency Fusion and Bootstrap Learning基于多尺度判别显著性融合和Bootstrap学习的深度感知显著目标检测和分割
PREAI
分享收藏Random Access Memories: A New Paradigm for Target Detection in High Resolution Aerial Remote Sensing Images随机存取存储器: 高分辨率航空遥感图像中目标检测的新范式
PREAI
分享收藏分享收藏
查看更多内容