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

TL;DR

This paper introduces a superpixel hierarchy method that preserves the high-dimensional attribute manifold of images, enabling more consistent exploration of large high-dimensional images in both image and attribute spaces.

Contribution

The proposed superpixel hierarchy incorporates spatial layout into hierarchical embedding, improving exploration of high-dimensional images over attribute-only methods.

Findings

Enhanced exploration of high-dimensional images in both image and attribute spaces.

Effective in handling datasets with several million pixels.

Outperforms classical hierarchical embedding methods in use cases.

Abstract

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.