Scene Complexity: A New Perspective on Understanding the Scene Semantics of Remote Sensing and Designing Image-Adaptive Convolutional Neural Networks
文献类型：期刊论文
| 作者 | Peng, Jian5; Mei, Xiaoming5; Li, Wenbo4 ; Hong, Liang1,2,3; Sun, Bingyu4; Li, Haifeng5
|
| 刊名 | REMOTE SENSING
 |
| 出版日期 | 2021-02-01 |
| 卷号 | 13 |
| 关键词 | scene understanding feature learning scene complexity adaptive networks |
| DOI | 10.3390/rs13040742 |
| 通讯作者 | Li, Haifeng(lihaifeng@csu.edu.cn) |
| 英文摘要 | Scene understanding of remote sensing images is of great significance in various applications. Its fundamental problem is how to construct representative features. Various convolutional neural network architectures have been proposed for automatically learning features from images. However, is the current way of configuring the same architecture to learn all the data while ignoring the differences between images the right one? It seems to be contrary to our intuition: it is clear that some images are easier to recognize, and some are harder to recognize. This problem is the gap between the characteristics of the images and the learning features corresponding to specific network structures. Unfortunately, the literature so far lacks an analysis of the two. In this paper, we explore this problem from three aspects: we first build a visual-based evaluation pipeline of scene complexity to characterize the intrinsic differences between images; then, we analyze the relationship between semantic concepts and feature representations, i.e., the scalability and hierarchy of features which the essential elements in CNNs of different architectures, for remote sensing scenes of different complexity; thirdly, we introduce CAM, a visualization method that explains feature learning within neural networks, to analyze the relationship between scenes with different complexity and semantic feature representations. The experimental results show that a complex scene would need deeper and multi-scale features, whereas a simpler scene would need lower and single-scale features. Besides, the complex scene concept is more dependent on the joint semantic representation of multiple objects. Furthermore, we propose the framework of scene complexity prediction for an image and utilize it to design a depth and scale-adaptive model. It achieves higher performance but with fewer parameters than the original model, demonstrating the potential significance of scene complexity. |
| 资助项目 | National Natural Science Foundation of China[61773360] ; National Natural Science Foundation of China[41871302] ; National Natural Science Foundation of China[41871276] |
| WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:000624473300001 |
| 出版者 | MDPI |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/120164]  |
| 专题 | 中国科学院合肥物质科学研究院 |
| 通讯作者 | Li, Haifeng |
| 作者单位 | 1.Yunnan Normal Univ, Sch Informat Sci & Technol, Kunming 650500, Yunnan, Peoples R China 2.Minist Educ, GIS Technol Res Ctr Resource & Environm Western C, Kunming 650500, Yunnan, Peoples R China 3.Yunnan Normal Univ, Sch Tourism & Geog, Kunming 650500, Yunnan, Peoples R China 4.Chinese Acad Sci, Hefei Inst Phys Sci, Inst Technol Innovat, Hefei 230088, Peoples R China 5.Cent South Univ, Sch Geosci & Info Phys, Changsha 410083, Peoples R China |
| 推荐引用方式 GB/T 7714 | Peng, Jian,Mei, Xiaoming,Li, Wenbo,et al. Scene Complexity: A New Perspective on Understanding the Scene Semantics of Remote Sensing and Designing Image-Adaptive Convolutional Neural Networks[J]. REMOTE SENSING,2021,13. |
| APA | Peng, Jian,Mei, Xiaoming,Li, Wenbo,Hong, Liang,Sun, Bingyu,&Li, Haifeng.(2021).Scene Complexity: A New Perspective on Understanding the Scene Semantics of Remote Sensing and Designing Image-Adaptive Convolutional Neural Networks.REMOTE SENSING,13. |
| MLA | Peng, Jian,et al."Scene Complexity: A New Perspective on Understanding the Scene Semantics of Remote Sensing and Designing Image-Adaptive Convolutional Neural Networks".REMOTE SENSING 13(2021). |
入库方式： OAI收割
来源：合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。