The trade-off between feature representation power and spatial localization accuracy is crucial for the dense classification/semantic segmentation of remote sensing images (RSIs). High-level features extracted from the late layers of a neural network are rich in semantic information, yet have blurred spatial details; low-level features extracted from the early layers of a network contain more pixel-level information but are isolated and noisy. It is therefore difficult to bridge the gap between high- and low-level features due to their difference in terms of physical information content and spatial distribution. In this article, we contribute to solve this problem by enhancing the feature representation in two ways. On the one hand, a patch attention module (PAM) is proposed to enhance the embedding of context information based on a patchwise calculation of local attention. On the other hand, an attention embedding module (AEM) is proposed to enrich the semantic information of low-level features by embedding local focus from high-level features. Both proposed modules are lightweight and can be applied to process the extracted features of convolutional neural networks (CNNs). Experiments show that, by integrating the proposed modules into a baseline fully convolutional network (FCN), the resulting local attention network (LANet) greatly improves the performance over the baseline and outperforms other attention-based methods on two RSI data sets.

LANet: Local Attention Embedding to Improve the Semantic Segmentation of Remote Sensing Images / Ding, Lei; Tang, Hao; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 1558-0644. - 2021/59:1(2021), pp. 426-435. [10.1109/TGRS.2020.2994150]

LANet: Local Attention Embedding to Improve the Semantic Segmentation of Remote Sensing Images

Lei Ding;Hao Tang;Lorenzo Bruzzone
2021

Abstract

The trade-off between feature representation power and spatial localization accuracy is crucial for the dense classification/semantic segmentation of remote sensing images (RSIs). High-level features extracted from the late layers of a neural network are rich in semantic information, yet have blurred spatial details; low-level features extracted from the early layers of a network contain more pixel-level information but are isolated and noisy. It is therefore difficult to bridge the gap between high- and low-level features due to their difference in terms of physical information content and spatial distribution. In this article, we contribute to solve this problem by enhancing the feature representation in two ways. On the one hand, a patch attention module (PAM) is proposed to enhance the embedding of context information based on a patchwise calculation of local attention. On the other hand, an attention embedding module (AEM) is proposed to enrich the semantic information of low-level features by embedding local focus from high-level features. Both proposed modules are lightweight and can be applied to process the extracted features of convolutional neural networks (CNNs). Experiments show that, by integrating the proposed modules into a baseline fully convolutional network (FCN), the resulting local attention network (LANet) greatly improves the performance over the baseline and outperforms other attention-based methods on two RSI data sets.
1
Ding, Lei; Tang, Hao; Bruzzone, Lorenzo
LANet: Local Attention Embedding to Improve the Semantic Segmentation of Remote Sensing Images / Ding, Lei; Tang, Hao; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 1558-0644. - 2021/59:1(2021), pp. 426-435. [10.1109/TGRS.2020.2994150]
File in questo prodotto:
File Dimensione Formato  
LANet_Local Attention Embedding to Improve the Semantic Segmentation of Remote Sensing Images.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 7.67 MB
Formato Adobe PDF
7.67 MB Adobe PDF Visualizza/Apri
LANet_Local_Attention_Embedding_to_Improve_the_Semantic_Segmentation_of_Remote_Sensing_Images.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 7.6 MB
Formato Adobe PDF
7.6 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11572/279199
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 50
  • ???jsp.display-item.citation.isi??? 51
social impact