View in EDS

HyperTaFOR: Task-Adaptive Few-Shot Open-Set Recognition With Spatial-Spectral Selective Transformer for Hyperspectral Imagery.

Saved in:
Bibliographic Details
Title: HyperTaFOR: Task-Adaptive Few-Shot Open-Set Recognition With Spatial-Spectral Selective Transformer for Hyperspectral Imagery.
Authors: Xi, Bobo1 xibobo@xidian.edu.cn, Zhang, Wenjie1 23011211025@stu.xidian.edu.cn, Li, Jiaojiao2 jjli@xidian.edu.cn, Song, Rui2 ruiScientifc@gmail.com, Li, Yunsong2 ysli@mail.xidian.edu.cn
Source: IEEE Transactions on Image Processing. 2025, Vol. 34, p4148-4160. 13p.
Subjects: Image recognition (Computer vision), Optical pattern recognition, Object recognition (Computer vision), Image registration, Hyperspectral imaging systems
Abstract: Open-set recognition (OSR) aims to accurately classify known categories while effectively rejecting unknown negative samples. Existing methods for OSR in hyperspectral images (HSI) can be generally divided into two categories: reconstruction-based and distance-based methods. Reconstruction-based approaches focus on analyzing reconstruction errors during inference, whereas distance-based methods determine the rejection of unknown samples by measuring their distance to each prototype. However, these techniques often require a substantial amount of training data, which can be both time-consuming and expensive to gather, and they require manual threshold setting, which can be difficult for different tasks. Furthermore, effectively utilizing spectral-spatial information in HSI remains a significant challenge, particularly in open-set scenarios. To tackle these challenges, we introduce a few-shot OSR framework for HSI named HyperTaFOR, which incorporates a novel spatial-spectral selective transformer (S3Former). This framework employs a meta-learning strategy to implement a negative prototype generation module (NPGM) that generates task-adaptive rejection scores, allowing flexible categorization of samples into various known classes and anomalies for each task. Additionally, the S3Former is designed to extract spectral-spatial features, optimizing the use of central pixel information while reducing the impact of irrelevant spatial data. Comprehensive experiments conducted on three benchmark hyperspectral datasets show that our proposed method delivers competitive classification and detection performance in open-set environments when compared to state-of-the-art methods. The code is available online at https://github.com/B-Xi/TIP_2025_HyperTaFOR. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Image Processing is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 191897126
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: HyperTaFOR: Task-Adaptive Few-Shot Open-Set Recognition With Spatial-Spectral Selective Transformer for Hyperspectral Imagery.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Xi%2C+Bobo%22">Xi, Bobo</searchLink><relatesTo>1</relatesTo><i> xibobo@xidian.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Wenjie%22">Zhang, Wenjie</searchLink><relatesTo>1</relatesTo><i> 23011211025@stu.xidian.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Jiaojiao%22">Li, Jiaojiao</searchLink><relatesTo>2</relatesTo><i> jjli@xidian.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Song%2C+Rui%22">Song, Rui</searchLink><relatesTo>2</relatesTo><i> ruiScientifc@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Yunsong%22">Li, Yunsong</searchLink><relatesTo>2</relatesTo><i> ysli@mail.xidian.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Image+Processing%22">IEEE Transactions on Image Processing</searchLink>. 2025, Vol. 34, p4148-4160. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Image+recognition+%28Computer+vision%29%22">Image recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Optical+pattern+recognition%22">Optical pattern recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Image+registration%22">Image registration</searchLink><br /><searchLink fieldCode="DE" term="%22Hyperspectral+imaging+systems%22">Hyperspectral imaging systems</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Open-set recognition (OSR) aims to accurately classify known categories while effectively rejecting unknown negative samples. Existing methods for OSR in hyperspectral images (HSI) can be generally divided into two categories: reconstruction-based and distance-based methods. Reconstruction-based approaches focus on analyzing reconstruction errors during inference, whereas distance-based methods determine the rejection of unknown samples by measuring their distance to each prototype. However, these techniques often require a substantial amount of training data, which can be both time-consuming and expensive to gather, and they require manual threshold setting, which can be difficult for different tasks. Furthermore, effectively utilizing spectral-spatial information in HSI remains a significant challenge, particularly in open-set scenarios. To tackle these challenges, we introduce a few-shot OSR framework for HSI named HyperTaFOR, which incorporates a novel spatial-spectral selective transformer (S3Former). This framework employs a meta-learning strategy to implement a negative prototype generation module (NPGM) that generates task-adaptive rejection scores, allowing flexible categorization of samples into various known classes and anomalies for each task. Additionally, the S3Former is designed to extract spectral-spatial features, optimizing the use of central pixel information while reducing the impact of irrelevant spatial data. Comprehensive experiments conducted on three benchmark hyperspectral datasets show that our proposed method delivers competitive classification and detection performance in open-set environments when compared to state-of-the-art methods. The code is available online at https://github.com/B-Xi/TIP_2025_HyperTaFOR. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Image Processing is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191897126
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TIP.2025.3555069
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 4148
    Subjects:
      – SubjectFull: Image recognition (Computer vision)
        Type: general
      – SubjectFull: Optical pattern recognition
        Type: general
      – SubjectFull: Object recognition (Computer vision)
        Type: general
      – SubjectFull: Image registration
        Type: general
      – SubjectFull: Hyperspectral imaging systems
        Type: general
    Titles:
      – TitleFull: HyperTaFOR: Task-Adaptive Few-Shot Open-Set Recognition With Spatial-Spectral Selective Transformer for Hyperspectral Imagery.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Xi, Bobo
      – PersonEntity:
          Name:
            NameFull: Zhang, Wenjie
      – PersonEntity:
          Name:
            NameFull: Li, Jiaojiao
      – PersonEntity:
          Name:
            NameFull: Song, Rui
      – PersonEntity:
          Name:
            NameFull: Li, Yunsong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: 2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 10577149
          Numbering:
            – Type: volume
              Value: 34
          Titles:
            – TitleFull: IEEE Transactions on Image Processing
              Type: main
ResultId 1