View in EDS

MCPT: Mixed Convolutional Parallel Transformer for Polarimetric SAR Image Classification

Saved in:
Bibliographic Details
Title: MCPT: Mixed Convolutional Parallel Transformer for Polarimetric SAR Image Classification
Authors: Wenke Wang, Jianlong Wang, Bibo Lu, Boyuan Liu, Yake Zhang, Chunyang Wang
Source: Remote Sensing, Vol 15, Iss 11, p 2936 (2023)
Publisher Information: MDPI AG
Publication Year: 2023
Collection: Directory of Open Access Journals: DOAJ Articles
Subject Terms: polarimetric SAR, convolutional neural network, vision transformer, mixed depthwise convolution tokenization, parallel encoder, global average pooling, Science
Description: Vision transformers (ViT) have the characteristics of massive training data and complex model, which cannot be directly applied to polarimetric synthetic aperture radar (PolSAR) image classification tasks. Therefore, a mixed convolutional parallel transformer (MCPT) model based on ViT is proposed for fast PolSAR image classification. First of all, a mixed depthwise convolution tokenization is introduced. It replaces the learnable linear projection in the original ViT to obtain patch embeddings. The process of tokenization can reduce computational and parameter complexity and extract features of different receptive fields as input to the encoder. Furthermore, combining the idea of shallow networks with lower latency and easier optimization, a parallel encoder is implemented by pairing the same modules and recombining to form parallel blocks, which can decrease the network depth and computing power requirement. In addition, the original class embedding and position embedding are removed during tokenization, and a global average pooling layer is added after the encoder for category feature extraction. Finally, the experimental results on AIRSAR Flevoland and RADARSAT-2 San Francisco datasets show that the proposed method achieves a significant improvement in training and prediction speed. Meanwhile, the overall accuracy achieved was 97.9% and 96.77%, respectively.
Document Type: article in journal/newspaper
Language: English
Relation: https://www.mdpi.com/2072-4292/15/11/2936; https://doaj.org/toc/2072-4292; https://doaj.org/article/1d3f011a206e47dd9deda43a270647b0
DOI: 10.3390/rs15112936
Availability: https://doi.org/10.3390/rs15112936
https://doaj.org/article/1d3f011a206e47dd9deda43a270647b0
Accession Number: edsbas.FC53F6DB
Database: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://doi.org/10.3390/rs15112936#
    Name: EDS - BASE (s4221598)
    Category: fullText
    Text: View record from BASE
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Wang%20W
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsbas
DbLabel: BASE
An: edsbas.FC53F6DB
RelevancyScore: 944
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 943.653564453125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: MCPT: Mixed Convolutional Parallel Transformer for Polarimetric SAR Image Classification
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Wenke+Wang%22">Wenke Wang</searchLink><br /><searchLink fieldCode="AR" term="%22Jianlong+Wang%22">Jianlong Wang</searchLink><br /><searchLink fieldCode="AR" term="%22Bibo+Lu%22">Bibo Lu</searchLink><br /><searchLink fieldCode="AR" term="%22Boyuan+Liu%22">Boyuan Liu</searchLink><br /><searchLink fieldCode="AR" term="%22Yake+Zhang%22">Yake Zhang</searchLink><br /><searchLink fieldCode="AR" term="%22Chunyang+Wang%22">Chunyang Wang</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Remote Sensing, Vol 15, Iss 11, p 2936 (2023)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: MDPI AG
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2023
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Directory of Open Access Journals: DOAJ Articles
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22polarimetric+SAR%22">polarimetric SAR</searchLink><br /><searchLink fieldCode="DE" term="%22convolutional+neural+network%22">convolutional neural network</searchLink><br /><searchLink fieldCode="DE" term="%22vision+transformer%22">vision transformer</searchLink><br /><searchLink fieldCode="DE" term="%22mixed+depthwise+convolution+tokenization%22">mixed depthwise convolution tokenization</searchLink><br /><searchLink fieldCode="DE" term="%22parallel+encoder%22">parallel encoder</searchLink><br /><searchLink fieldCode="DE" term="%22global+average+pooling%22">global average pooling</searchLink><br /><searchLink fieldCode="DE" term="%22Science%22">Science</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Vision transformers (ViT) have the characteristics of massive training data and complex model, which cannot be directly applied to polarimetric synthetic aperture radar (PolSAR) image classification tasks. Therefore, a mixed convolutional parallel transformer (MCPT) model based on ViT is proposed for fast PolSAR image classification. First of all, a mixed depthwise convolution tokenization is introduced. It replaces the learnable linear projection in the original ViT to obtain patch embeddings. The process of tokenization can reduce computational and parameter complexity and extract features of different receptive fields as input to the encoder. Furthermore, combining the idea of shallow networks with lower latency and easier optimization, a parallel encoder is implemented by pairing the same modules and recombining to form parallel blocks, which can decrease the network depth and computing power requirement. In addition, the original class embedding and position embedding are removed during tokenization, and a global average pooling layer is added after the encoder for category feature extraction. Finally, the experimental results on AIRSAR Flevoland and RADARSAT-2 San Francisco datasets show that the proposed method achieves a significant improvement in training and prediction speed. Meanwhile, the overall accuracy achieved was 97.9% and 96.77%, respectively.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article in journal/newspaper
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://www.mdpi.com/2072-4292/15/11/2936; https://doaj.org/toc/2072-4292; https://doaj.org/article/1d3f011a206e47dd9deda43a270647b0
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3390/rs15112936
– Name: URL
  Label: Availability
  Group: URL
  Data: https://doi.org/10.3390/rs15112936<br />https://doaj.org/article/1d3f011a206e47dd9deda43a270647b0
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.FC53F6DB
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.FC53F6DB
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs15112936
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: polarimetric SAR
        Type: general
      – SubjectFull: convolutional neural network
        Type: general
      – SubjectFull: vision transformer
        Type: general
      – SubjectFull: mixed depthwise convolution tokenization
        Type: general
      – SubjectFull: parallel encoder
        Type: general
      – SubjectFull: global average pooling
        Type: general
      – SubjectFull: Science
        Type: general
    Titles:
      – TitleFull: MCPT: Mixed Convolutional Parallel Transformer for Polarimetric SAR Image Classification
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Wenke Wang
      – PersonEntity:
          Name:
            NameFull: Jianlong Wang
      – PersonEntity:
          Name:
            NameFull: Bibo Lu
      – PersonEntity:
          Name:
            NameFull: Boyuan Liu
      – PersonEntity:
          Name:
            NameFull: Yake Zhang
      – PersonEntity:
          Name:
            NameFull: Chunyang Wang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
          Titles:
            – TitleFull: Remote Sensing, Vol 15, Iss 11, p 2936 (2023
              Type: main
ResultId 1