Blind-Spot KAN-Based Background Reconstruction Network with Prior Purification for Hyperspectral Anomaly Detection.
Saved in:
| Title: | Blind-Spot KAN-Based Background Reconstruction Network with Prior Purification for Hyperspectral Anomaly Detection. |
|---|---|
| Authors: | Yu, Lifeng1 (AUTHOR), Liu, Yifan2 (AUTHOR), Gao, Hongmin1,2 (AUTHOR) gaohongmin@hhu.edu.cn |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 10, p1628. 19p. |
| Subjects: | Outlier detection, Image reconstruction, Deep learning |
| Abstract: | Highlights: What are the main findings? We proposed BKP-Net for hyperspectral anomaly detection (HAD), integrating a Background Prior Purification (BPP) module and a Blind-Spot KAN-based Reconstruction (BKCN) backbone to mitigate "anomaly leakage" from both data and model perspectives. We leveraged Kolmogorov–Arnold Networks (KANs) for nonlinear background modeling and introduced a Guided Reconstruction Refinement (GRR) strategy to enhance structural consistency and boundary preservation. What are the implications of the main findings? BKP-Net achieves state-of-the-art performance across multiple HSI datasets, demonstrating superior background suppression and anomaly separability, especially for complex backgrounds and contiguous targets. Ablation studies confirm that the synergistic integration of BPP, BKCN, and GRR effectively mitigates both training data contamination and representation-induced leakage. Hyperspectral anomaly detection (HAD) aims to identify rare targets without relying on prior target knowledge. However, background spectra in hyperspectral images often lie on highly complex and nonlinear manifolds, making accurate modeling challenging. Although models with strong nonlinear approximation capabilities, such as Kolmogorov–Arnold Networks (KANs), provide a promising solution for capturing such complexity, self-supervised reconstruction-based HAD methods still suffer from a fundamental issue known as anomaly leakage. When the model has high representation capacity, anomalous signatures tend to be partially reconstructed, which reduces residual contrast and degrades detection performance. To address this issue, we propose a Blind-Spot KAN-based background reconstruction network with prior purification (BKP-Net), which mitigates anomaly leakage from both data and model perspectives. Specifically, we first introduce a Background Prior Purification (BPP) module to construct a cleaner background prior. This module suppresses and replaces potential outlier pixels through spatial clustering and robust weighted mean estimation. We then design a Blind-Spot KAN-based Reconstruction backbone (BKCN) to model complex nonlinear background characteristics while preventing direct information flow from the center pixel, thereby reducing anomaly leakage during reconstruction. In addition, separable convolutions are employed to enhance spatial–spectral feature representation, followed by an attention-guided fusion mechanism to suppress cross-domain interference. Furthermore, a band-wise Guided Reconstruction Refinement (GRR) strategy is introduced in the detection phase to improve structural consistency between the reconstructed background and the original hyperspectral image, leading to more reliable anomaly discrimination. Experimental results on four hyperspectral datasets demonstrate that the proposed method achieves competitive performance compared with several representative traditional and deep learning-based detectors. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI 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 |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194141153 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Blind-Spot KAN-Based Background Reconstruction Network with Prior Purification for Hyperspectral Anomaly Detection. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Yu%2C+Lifeng%22">Yu, Lifeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Yifan%22">Liu, Yifan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gao%2C+Hongmin%22">Gao, Hongmin</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> gaohongmin@hhu.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. May2026, Vol. 18 Issue 10, p1628. 19p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Outlier+detection%22">Outlier detection</searchLink><br /><searchLink fieldCode="DE" term="%22Image+reconstruction%22">Image reconstruction</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? We proposed BKP-Net for hyperspectral anomaly detection (HAD), integrating a Background Prior Purification (BPP) module and a Blind-Spot KAN-based Reconstruction (BKCN) backbone to mitigate "anomaly leakage" from both data and model perspectives. We leveraged Kolmogorov–Arnold Networks (KANs) for nonlinear background modeling and introduced a Guided Reconstruction Refinement (GRR) strategy to enhance structural consistency and boundary preservation. What are the implications of the main findings? BKP-Net achieves state-of-the-art performance across multiple HSI datasets, demonstrating superior background suppression and anomaly separability, especially for complex backgrounds and contiguous targets. Ablation studies confirm that the synergistic integration of BPP, BKCN, and GRR effectively mitigates both training data contamination and representation-induced leakage. Hyperspectral anomaly detection (HAD) aims to identify rare targets without relying on prior target knowledge. However, background spectra in hyperspectral images often lie on highly complex and nonlinear manifolds, making accurate modeling challenging. Although models with strong nonlinear approximation capabilities, such as Kolmogorov–Arnold Networks (KANs), provide a promising solution for capturing such complexity, self-supervised reconstruction-based HAD methods still suffer from a fundamental issue known as anomaly leakage. When the model has high representation capacity, anomalous signatures tend to be partially reconstructed, which reduces residual contrast and degrades detection performance. To address this issue, we propose a Blind-Spot KAN-based background reconstruction network with prior purification (BKP-Net), which mitigates anomaly leakage from both data and model perspectives. Specifically, we first introduce a Background Prior Purification (BPP) module to construct a cleaner background prior. This module suppresses and replaces potential outlier pixels through spatial clustering and robust weighted mean estimation. We then design a Blind-Spot KAN-based Reconstruction backbone (BKCN) to model complex nonlinear background characteristics while preventing direct information flow from the center pixel, thereby reducing anomaly leakage during reconstruction. In addition, separable convolutions are employed to enhance spatial–spectral feature representation, followed by an attention-guided fusion mechanism to suppress cross-domain interference. Furthermore, a band-wise Guided Reconstruction Refinement (GRR) strategy is introduced in the detection phase to improve structural consistency between the reconstructed background and the original hyperspectral image, leading to more reliable anomaly discrimination. Experimental results on four hyperspectral datasets demonstrate that the proposed method achieves competitive performance compared with several representative traditional and deep learning-based detectors. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Remote Sensing is the property of MDPI 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=194141153 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18101628 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 19 StartPage: 1628 Subjects: – SubjectFull: Outlier detection Type: general – SubjectFull: Image reconstruction Type: general – SubjectFull: Deep learning Type: general Titles: – TitleFull: Blind-Spot KAN-Based Background Reconstruction Network with Prior Purification for Hyperspectral Anomaly Detection. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Yu, Lifeng – PersonEntity: Name: NameFull: Liu, Yifan – PersonEntity: Name: NameFull: Gao, Hongmin IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 05 Text: May2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 10 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
