APDC-Net: Attention Pooling-Based Convolutional Network for Aerial Scene Classification

Deep learning methods have boosted the performance of a series of visual tasks. However, the aerial image scene classification remains challenging. The object distribution and spatial arrangement in aerial scenes are often more complicated than in natural image scenes. Possible solutions include hig...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2020-09, Vol.17 (9), p.1603-1607
Main Authors: Bi, Qi, Qin, Kun, Zhang, Han, Xie, Jiafen, Li, Zhili, Xu, Kai
Format: Article
Language:English
Subjects:
Aerial image
attention-based pooling
Benchmark testing
Benchmarks
Classification
convolutional neural network
Deep learning
dense connection
Feature extraction
Feature maps
Geographical distribution
Image classification
Machine learning
Methods
multi-level supervision
Probability distribution
scene classification
Semantics
Task analysis
Training
Visual tasks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning methods have boosted the performance of a series of visual tasks. However, the aerial image scene classification remains challenging. The object distribution and spatial arrangement in aerial scenes are often more complicated than in natural image scenes. Possible solutions include highlighting local semantics relevant to the scene label and preserving more discriminative features. To tackle this challenge, in this letter, we propose an attention pooling-based dense connected convolutional network (APDC-Net) for aerial scene classification. First, it uses a simplified dense connection structure as the backbone to preserve features from different levels. Then, we propose a trainable pooling to down-sample the feature maps and to enhance the local semantic representation capability. Finally, we introduce a multi-level supervision strategy, so that features from different levels are all allowed to supervise the training process directly. Exhaustive experiments on three aerial scene classification benchmarks demonstrate that our proposed APDC-Net outperforms other state-of-the-art methods with much fewer parameters and validate the effectiveness of our attention-based pooling and multi-level supervision strategy.
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2019.2949930