# Triplet-Watershed for Hyperspectral Image Classification

arXiv: https://arxiv.org/abs/2103.09384 · HTML: https://mlsanity.com/paper/2103.09384/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 82 references that are in the map.
- First posted on arXiv 17 Mar 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification](https://mlsanity.com/paper/2008.05457/) (2020)
- [Deep Learning for Hyperspectral Image Classification: An Overview](https://mlsanity.com/paper/1910.12861/) (2019)
- [Graph Convolutional Networks for Hyperspectral Image Classification](https://mlsanity.com/paper/2008.02457/) (2020)
- [Three dimensional Deep Learning approach for remote sensing image classification](https://mlsanity.com/paper/1806.05824/) (2018)
- [Convolutional Oriented Boundaries](https://mlsanity.com/paper/1608.02755/) (2016)
- [Validating Hyperspectral Image Segmentation](https://mlsanity.com/paper/1811.03707/) (2018)
- [Learnable Manifold Alignment (LeMA) : A Semi-supervised Cross-modality Learning Framework for Land Cover and Land Use Classification](https://mlsanity.com/paper/1901.02838/) (2019)
- [CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences](https://mlsanity.com/paper/1812.11501/) (2018)
- [BS-Nets: An End-to-End Framework For Band Selection of Hyperspectral Image](https://mlsanity.com/paper/1904.08269/) (2019)
- [Joint and Progressive Subspace Analysis (JPSA) with Spatial-Spectral Manifold Alignment for Semi-Supervised Hyperspectral Dimensionality Reduction](https://mlsanity.com/paper/2009.10003/) (2020)
- [Efficient Deep Learning of Non-local Features for Hyperspectral Image Classification](https://mlsanity.com/paper/2008.00542/) (2020)
- [Learned Watershed: End-to-End Learning of Seeded Segmentation](https://mlsanity.com/paper/1704.02249/) (2017)
- [Semi-supervised Hyperspectral Image Classification with Graph Clustering Convolutional Networks](https://mlsanity.com/paper/2012.10932/) (2020)
- [Morphological segmentation of hyperspectral images](https://mlsanity.com/paper/2010.00853/) (2020)

## Built on by (most cited first, 2 of 2)

- [A Novel Approach to Regularising 1NN classifier for Improved Generalization](https://mlsanity.com/paper/2402.08405/) (2024)
- [Playing with Kruskal: algorithms for flat and hierarchical watershed cuts](https://mlsanity.com/paper/2610.10012/) (2026)

## Abstract (arXiv)

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.