EUVIMEDEUVIMED entdecken
Crossref

Adaptive Coarse-to-Fine Parameter Optimization for Incremental Hyperspectral Target Detection

Jiahui Qu, Yonghui Chen, Wenqian Dong, Yunsong Li, Qian Du

IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 9378-9391

DOI: 10.1109/tcsvt.2026.3671092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Jiahui Qu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Young Talent Fund of Association for Science and Technology in Shaanxi, Key Research and Development Projects of Shaanxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral target detection effectively identifies fixed targets using specific spectral signatures but suffers from catastrophic forgetting when detecting multiple targets of interest within the same scene. Traditional data replay strategies may further exacerbate training instability due to mislabeled samples. To address these limitations, we propose an Adaptive Coarse-to-Fine Parameter Optimization framework (ACFPO) for incremental hyperspectral target detection, which enables stable continual learning via structural adaptation and parameter sensitivity–aware refinement. ACFPO formulates the task as a dual-stage process: coarse-grained matching and fine-grained detection. Specifically, an Adaptive Spectral Prior-Guided Coarse Matching (AS-PCM) module is designed to hierarchically organize detection tasks into semantic domains and construct intra- and inter-class spectral pairs for coarse-level alignment to adaptively select optimal submodels. Subsequently, a Distance-Aware Localized Fine-Grained Parameter Optimization (DA-LFPO) module is proposed to identify layer-wise sensitive parameters of the selected submodels by measuring spectral–spatial discrepancy, enabling selective retraining to preserve model stability on previously learned classes. By dynamically freezing non-sensitive parameters and optimizing critical modules, our approach mitigates inherent model drift and gradient conflicts in replay-based methods. Extensive experiments on three benchmark datasets demonstrate the superior performance of ACFPO, achieving a balanced trade-off between stability of the existing target and the adaptability of incremental targets. The code is available at https://github.com/Jiahuiqu/ACFPO

Förderung

  • National Natural Science Foundation of China
  • Young Talent Fund of Association for Science and Technology in Shaanxi
  • Key Research and Development Projects of Shaanxi Province
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Qu, J., Chen, Y., Dong, W., Li, Y., & Du, Q. (2026). Adaptive Coarse-to-Fine Parameter Optimization for Incremental Hyperspectral Target Detection. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 9378-9391. https://doi.org/10.1109/tcsvt.2026.3671092

Vancouver

Qu J, Chen Y, Dong W, Li Y, Du Q. Adaptive Coarse-to-Fine Parameter Optimization for Incremental Hyperspectral Target Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):9378-9391. doi:10.1109/tcsvt.2026.3671092

BibTeX
@article{Qu2026,
  author = {Qu, Jiahui and Chen, Yonghui and Dong, Wenqian and Li, Yunsong and Du, Qian},
  title = {Adaptive Coarse-to-Fine Parameter Optimization for Incremental Hyperspectral Target Detection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {7},
  pages = {9378--9391},
  doi = {10.1109/tcsvt.2026.3671092}
}
Kostenlos starten →