Preprint Article Version 3 This version is not peer-reviewed

Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning

Version 1 : Received: 5 December 2018 / Approved: 7 December 2018 / Online: 7 December 2018 (03:51:17 CET)
Version 2 : Received: 25 December 2018 / Approved: 25 December 2018 / Online: 25 December 2018 (13:59:28 CET)
Version 3 : Received: 3 January 2019 / Approved: 4 January 2019 / Online: 4 January 2019 (11:47:42 CET)

A peer-reviewed article of this Preprint also exists.

Panboonyuen, T.; Jitkajornwanich, K.; Lawawirojwong, S.; Srestasathiern, P.; Vateekul, P. Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning. Remote Sens. 2019, 11, 83. Panboonyuen, T.; Jitkajornwanich, K.; Lawawirojwong, S.; Srestasathiern, P.; Vateekul, P. Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning. Remote Sens. 2019, 11, 83.

Journal reference: Remote Sens. 2019, 11, 83
DOI: 10.3390/rs11010083

Abstract

In the remote sensing domain, it is crucial to complete semantic segmentation on the raster images, e.g., river, building, forest, etc, on raster images. A deep convolutional encoder--decoder (DCED) network is the state-of-the-art semantic segmentation method for remotely sensed images. However, the accuracy is still limited, since the network is not designed for remotely sensed images and the training data in this domain is deficient. In this paper, we aim to propose a novel CNN for semantic segmentation particularly for remote sensing corpora with three main contributions. First, we propose applying a recent CNN called a global convolutional network (GCN), since it can capture different resolutions by extracting multi-scale features from different stages of the network. Additionally, we further enhance the network by improving its backbone using larger numbers of layers, which is suitable for medium resolution remotely sensed images. Second, "channel attention'' is presented in our network in order to select the most discriminative filters (features). Third, "domain-specific transfer learning'' is introduced to alleviate the scarcity issue by utilizing other remotely sensed corpora with different resolutions as pre-trained data. The experiment was then conducted on two given datasets: (i) medium resolution data collected from Landsat-8 satellite and (ii) very high resolution data called the ISPRS Vaihingen Challenge Dataset. The results show that our networks outperformed DCED in terms of $F1$ for 17.48% and 2.49% on medium and very high resolution corpora, respectively.

Subject Areas

deep convolutional neural networks; multi-class segmentation; global convolutional network; channel attention; transfer learning; ISPRS Vaihingen; Landsat-8

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.