# Manifold-Preserving Superpixel Hierarchies and Embeddings for the Exploration of High-Dimensional Images

arXiv: https://arxiv.org/abs/2602.24160 · HTML: https://mlsanity.com/paper/2602.24160/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 52 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 13 of 13)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Superpixels: An Evaluation of the State-of-the-Art](https://mlsanity.com/paper/1612.01601/) (2016)
- [Approximated and User Steerable tSNE for Progressive Visual Analytics](https://mlsanity.com/paper/1512.01655/) (2015)
- [A Comparative Study for Unsupervised Network Representation Learning](https://mlsanity.com/paper/1903.07902/) (2019)
- [Superpixel Hierarchy](https://mlsanity.com/paper/1605.06325/) (2016)
- [Revisiting Random Walks for Learning on Graphs](https://mlsanity.com/paper/2407.01214/) (2024)
- [A Survey of Algorithms for Geodesic Paths and Distances](https://mlsanity.com/paper/2007.10430/) (2020)
- [A comprehensive review and new taxonomy on superpixel segmentation](https://mlsanity.com/paper/2409.19179/) (2024)
- [Unsupervised Segmentation of Hyperspectral Remote Sensing Images with Superpixels](https://mlsanity.com/paper/2204.12296/) (2022)
- [HUMAP: Hierarchical Uniform Manifold Approximation and Projection](https://mlsanity.com/paper/2106.07718/) (2021)

## Abstract (arXiv)

High-dimensional images, or images with a high-dimensional attribute vector per pixel, are commonly explored with coordinated views of a low-dimensional embedding of the attribute space and a conventional image representation. Nowadays, such images can easily contain several million pixels. For such large datasets, hierarchical embedding techniques are better suited to represent the high-dimensional attribute space than flat dimensionality reduction methods. However, available hierarchical dimensionality reduction methods construct the hierarchy purely based on the attribute information and ignore the spatial layout of pixels in the images. This impedes the exploration of regions of interest in the image space, since there is no congruence between a region of interest in image space and the associated attribute abstractions in the hierarchy. In this paper, we present a superpixel hierarchy for high-dimensional images that takes the high-dimensional attribute manifold into account during construction. Through this, our method enables consistent exploration of high-dimensional images in both image and attribute space. We show the effectiveness of this new image-guided hierarchy in the context of embedding exploration by comparing it with classical hierarchical embedding-based image exploration in two use cases.