Self-Supervised Masked Graph Autoencoder for Hyperspectral Anomaly Detection

Hyperspectral image anomaly detection faces the challenge of difficulty in annotating anomalous targets. Autoencoder (AE)-based methods are widely used due to their excellent image reconstruction capability. However, traditional grid-based image representation methods struggle to capture long-range...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - PP(2025) vom: 16. Okt.
1. Verfasser: Tu, Bing (VerfasserIn)
Weitere Verfasser: He, Baoliang, He, Yan, Zhou, Tao, Liu, Bo, Li, Jun, Plaza, Antonio
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM394155882
003 DE-627
005 20251017233332.0
007 cr uuu---uuuuu
008 251017s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2025.3620091  |2 doi 
028 5 2 |a pubmed25n1602.xml 
035 |a (DE-627)NLM394155882 
035 |a (NLM)41100244 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Tu, Bing  |e verfasserin  |4 aut 
245 1 0 |a Self-Supervised Masked Graph Autoencoder for Hyperspectral Anomaly Detection 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 16.10.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Hyperspectral image anomaly detection faces the challenge of difficulty in annotating anomalous targets. Autoencoder (AE)-based methods are widely used due to their excellent image reconstruction capability. However, traditional grid-based image representation methods struggle to capture long-range dependencies and model non-Euclidean structures. To address these issues, this paper proposes a self-supervised Masked Graph AutoEncoder (MGAE) for hyperspectral anomaly detection. MGAE utilizes a Graph Attention Network (GAT) autoencoder to reconstruct the background of hyperspectral images and identifies anomalies by comparing the reconstructed features with the original features. Specifically, we constructs a topological graph structure of the hyperspectral image, which is then input into the GAT autoencoder for reconstruction, leveraging the multi-head attention mechanism to learn spatial and spectral features. To prevent the decoder from learning trivial solutions, we introduce a re-masking strategy that randomly masks both the input features and hidden representations during training, forcing the model to learn and reconstruct features under limited information, thereby improving detection performance. Additionally, the proposed loss function with graph Laplacian regularization (Twice Loss) minimizes variations in feature representations, leading to more consistent background reconstruction. Experimental results on several real-world hyperspectral datasets demonstrate that MGAE outperforms existing methods 
650 4 |a Journal Article 
700 1 |a He, Baoliang  |e verfasserin  |4 aut 
700 1 |a He, Yan  |e verfasserin  |4 aut 
700 1 |a Zhou, Tao  |e verfasserin  |4 aut 
700 1 |a Liu, Bo  |e verfasserin  |4 aut 
700 1 |a Li, Jun  |e verfasserin  |4 aut 
700 1 |a Plaza, Antonio  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g PP(2025) vom: 16. Okt.  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:16  |g month:10 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2025.3620091  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2025  |b 16  |c 10