.png){kind=icon}
Return
A Plug-and-Play Data-Centric Training Framework for Efficient Hyperspectral Image Classification
.png){kind=icon}
OA
AI
DOI：10.1109/jstars.2026.3712611.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Current approaches predominantly treat hyperspectral image (HSI) classification as a standard computer vision task, relying on static training paradigms that ignore HSI’s unique physical attributes—specifically, severe spectral redundancy and high spatial correlation. This oversight leads to exorbitant computational costs. To break this bottleneck, we present the progressive adaptive constrained efficient (PACE) framework. As a plug-and-play scheme, PACE introduces dynamic training optimization, seamlessly integrating with various architectures without structural modifications. Specifically, PACE consists of three synergistic modules: first, the spatial-spectral dual-constraint data augmentation module leverages spatial homogeneity and continuous spectral signatures to generate physically consistent pseudo-labeled samples, effectively addressing data scarcity. Second, the Progressive gradient descent strategy implements a dynamic curriculum that progressively refines data sampling, substantially reducing computational redundancy. Third, the input–output coupled adaptive focusing mechanism adaptively focuses optimization on reliable features, ensuring stable convergence. Extensive experiments across 11 representative HSI classification architectures on four benchmark datasets demonstrate that PACE consistently achieves overall accuracy improvements of 1.33%, 1.08%, 1.91%, and 0.92% on the Salinas, Pavia University, WHU-LongKou, and HyRANK-Loukia datasets, respectively, alongside a total training time reduction of 35.92%, 21.39%, 22.14%, and 21.13% on these datasets, respectively, offering a practical and universal solution that effectively balances efficiency and accuracy in HSI classification.
Keywords:
Hyperspectral image (HSI) classification
plug-and-play
progressive learning
training acceleration
Journal
IF:
5.3
Papers:
1.8K
Citations:
3.0W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSaveShareSaveShareSaveShareSaveShareSave
View more