Deep learning has proven to be a very effective approach for Hyperspectral Image (HSI) classification. However, deep neural networks require large annotated datasets to generalize well. This limits the applicability of deep learning for HSI classification, where manually labelling thousands of pixels for every scene is impractical. In this paper, we propose to leverage Self Supervised Learning (SSL) for HSI classification. We show that by pre-training an encoder on unlabeled pixels using Barlow-Twins, a state-of-the-art SSL algorithm, we can obtain accurate models with a handful of labels. Experimental results demonstrate that this approach significantly outperforms vanilla supervised learning.
翻译:深层学习被证明是超光谱图像(HSI)分类的一个非常有效的方法。 但是,深神经网络需要大量的附加说明的数据集才能全面概括。 这限制了深入学习对高光谱图像分类的适用性, 而在高光谱图像分类中, 手工给每个场景贴上数千个像素标签是不切实际的。 在本文中, 我们提议利用自我监督学习(SSL)来进行高光谱图像分类。 我们通过对使用最先进的 SSL 算法Barlow- Twins (Barlow- Twins) 的无标签像素的编码器进行预培训来显示, 一种最先进的 SSL 算法( SSL), 我们可以用少数标签获得准确的模型。 实验结果表明, 这种方法大大超越了 Vanilla 监督下的学习。