用自蒸馏提升高光谱图像分类性能，解决数据少、过拟合问题。
SDHSI-Net: Learning Better Representations for Hyperspectral Images via Self-Distillation
- 用网络自身早期输出作软标签，引导中间与最终预测一致
- 在两个基准数据集上准确率显著提升，特征聚类更紧凑、区分度更高
- 适合高光谱图像处理初学者和需要轻量模型的研究者
高光谱图像（HSI）分类因光谱维度高且标注数据有限而面临独特挑战。传统深度学习模型常出现过拟合和计算开销大的问题。自蒸馏（SD）作为一种知识蒸馏变体，通过让网络从自身预测中学习，无需外部教师网络即可提升性能。本文将SD应用于HSI任务，将网络早期输出作为软目标，强制中间与最终预测保持一致性，从而增强特征空间内的类内紧凑性和类间可分性。该方法在两个基准高光谱图像数据集上验证，显著提升了分类准确率与鲁棒性，证明了自蒸馏在光谱-空间学习中的有效性。代码已开源：https://github.com/Prachet-Dev-Singh/SDHSI。
原文摘要 · Abstract (English)
Hyperspectral image (HSI) classification presents unique challenges due to its high spectral dimensionality and limited labeled data. Traditional deep learning models often suffer from overfitting and high computational costs. Self-distillation (SD), a variant of knowledge distillation where a network learns from its own predictions, has recently emerged as a promising strategy to enhance model performance without requiring external teacher networks. In this work, we explore the application of SD to HSI by treating earlier outputs as soft targets, thereby enforcing consistency between intermediate and final predictions. This process improves intra-class compactness and inter-class separability in the learned feature space. Our approach is validated on two benchmark HSI datasets and demonstrates significant improvements in classification accuracy and robustness, highlighting the effectiveness of SD for spectral-spatial learning. Codes are available at https://github.com/Prachet-Dev-Singh/SDHSI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。