HyperTaFOR: Task-Adaptive Few-Shot Open-Set Recognition With Spatial-Spectral Selective Transformer for Hyperspectral Imagery
IEEE Transactions on Image Processing · 2025 · 34 · 4148-4160
DOI: 10.1109/tip.2025.3555069 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Bobo Xi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
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.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- China Postdoctoral Science Foundation
- Natural Science Basic Research Plan in Shaanxi Province of China
- Guangdong Basic and Applied Basic Research Foundation
- Postdoctoral Science Foundation of Shaanxi Province
- Climbing Program of the National Space Science Center
- Youth Innovation Team of Shaanxi Universities
Zitieren
APA
Xi, B., Zhang, W., Li, J., Song, R., & Li, Y. (2025). HyperTaFOR: Task-Adaptive Few-Shot Open-Set Recognition With Spatial-Spectral Selective Transformer for Hyperspectral Imagery. IEEE Transactions on Image Processing, 34, 4148-4160. https://doi.org/10.1109/tip.2025.3555069
Vancouver
Xi B, Zhang W, Li J, Song R, Li Y. HyperTaFOR: Task-Adaptive Few-Shot Open-Set Recognition With Spatial-Spectral Selective Transformer for Hyperspectral Imagery. IEEE Transactions on Image Processing. 2025;34:4148-4160. doi:10.1109/tip.2025.3555069
BibTeX
@article{Xi2025,
author = {Xi, Bobo and Zhang, Wenjie and Li, Jiaojiao and Song, Rui and Li, Yunsong},
title = {HyperTaFOR: Task-Adaptive Few-Shot Open-Set Recognition With Spatial-Spectral Selective Transformer for Hyperspectral Imagery},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {4148--4160},
doi = {10.1109/tip.2025.3555069}
}
EUVIMED