Breaking the ImageNet Pretraining Paradigm: A General Framework for Training Using Only Remote Sensing Scene Images

Author:

Xu Tao12,Zhao Zhicheng123,Wu Jun13

Affiliation:

1. The 38th Research Institute of China Electronics Technology Group Corporation, Hefei 230088, China

2. Key Laboratory of Aperture Array and Space Application, Hefei 230088, China

3. Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Hefei 230039, China

Abstract

Remote sensing scene classification (RSSC) is a very crucial subtask of remote sensing image understanding. With the rapid development of convolutional neural networks (CNNs) in the field of natural images, great progress has been made in RSSC. Compared with natural images, labeled remote sensing images are more difficult to acquire, and typical RSSC datasets are consequently smaller than natural image datasets. Due to the small scale of these labeled datasets, training a network using only remote sensing scene datasets is very difficult. Most current approaches rely on a paradigm consisting of ImageNet pretraining followed by model fine-tuning on RSSC datasets. However, there are considerable dissimilarities between remote sensing images and natural images, and as a result, the current paradigm may present some problems for new studies. In this paper, to break free of this paradigm, we propose a general framework for scene classification (GFSC) that can help to train various network architectures on limited labeled remote sensing scene images. Extensive experiments show that ImageNet pretraining is not only unnecessary but may be one of the causes of the limited performance of RSSC models. Our study provides a solution that not only replaces the ImageNet pretraining paradigm but also further improves the baseline for RSSC. Our proposed framework can help various CNNs achieve state-of-the-art performance using only remote sensing images and endow the trained models with a stronger ability to extract discriminative features from complex remote sensing images.

Funder

Joint Funds of the National Natural Science Foundation of China

Natural Science Foundation of Anhui Province

National Natural Science Foundation of China

Natural Science Foundation of Education Department of Anhui Province

Publisher

MDPI AG

Subject

Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science

Reference60 articles.

1. Channel-attention-based DenseNet network for remote sensing image scene classification;Tong;IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,2020

2. Adjacent bi-hierarchical network for scene parsing of remote sensing images;Ma;IEEE Geosci. Remote Sens. Lett.,2023

3. Multiform Ensemble Self-Supervised Learning for Few-Shot Remote Sensing Scene Classification;Li;IEEE Trans. Geosci. Remote Sens.,2023

4. Object-guided remote sensing image scene classification based on joint use of deep-learning classifier and detector;Yang;IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,2020

5. Hierarchical Attention and Bilinear Fusion for Remote Sensing Image Scene Classification;Yu;IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,2020

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3