用于高光谱图像分类的 Triplet-Watershed
Triplet-Watershed for Hyperspectral Image Classification
AI总结：
针对高光谱图像分类中 softmax 分类层未变的问题，提出 Triplet-Watershed，用可学习表示配合无参数 watershed 分类器，以四分之一参数在四个数据集上达到监督与半监督先进性能。
摘要：
高光谱图像（HSI）包含丰富的空间和光谱信息，有可能用于多种应用。然而，噪声、波段相关性和高维性限制了此类数据的适用性。最近，ResNet、SSRN 和 A2S2K 等富有创造性的深度学习网络架构解决了这一问题。但是，最后一层（即分类层）仍保持不变，并被采用为 softmax 分类器。本文提出使用 watershed 分类器。Watershed 分类器扩展了数学形态学中的 watershed 算子以用于分类。在其原始形式中，watershed 分类器没有任何可训练参数。本文提出一种训练深度学习网络的新方法，以获得适合 watershed 分类器的表示。Watershed 分类器利用连通模式（HSI 数据集的一个特征）来实现更好的推理。我们表明，利用这些特征使 Triplet-Watershed 能够在监督和半监督场景下取得最先进结果。这些结果在 Indianpines（IP）、University of Pavia（UP）、Kennedy Space Center（KSC）和 University of Houston（UH）数据集上得到验证，所依赖的是简单卷积网络架构，其参数量仅为以往最先进网络的四分之一。用于复现实验的源代码和补充材料（高分辨率图像）可在 https://github.com/ac20/TripletWatershed Code 获取。
英文摘要：
Hyperspectral images (HSI) consist of rich spatial and spectral information, which can potentially be used for several applications. However, noise, band correlations and high dimensionality restrict the applicability of such data. This is recently addressed using creative deep learning network architectures such as ResNet, SSRN, and A2S2K. However, the last layer, i.e the classification layer, remains unchanged and is taken to be the softmax classifier. In this article, we propose to use a watershed classifier. Watershed classifier extends the watershed operator from Mathematical Morphology for classification. In its vanilla form, the watershed classifier does not have any trainable parameters. In this article, we propose a novel approach to train deep learning networks to obtain representations suitable for the watershed classifier. The watershed classifier exploits the connectivity patterns, a characteristic of HSI datasets, for better inference. We show that exploiting such characteristics allows the Triplet-Watershed to achieve state-of-art results in supervised and semi-supervised contexts. These results are validated on Indianpines (IP), University of Pavia (UP), Kennedy Space Center (KSC) and University of Houston (UH) datasets, relying on simple convnet architecture using a quarter of parameters compared to previous state-of-the-art networks. The source code for reproducing the experiments and supplementary material (high resolution images) is available at https://github.com/ac20/TripletWatershed Code.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
