Manifold-Preserving Superpixel Hierarchies and Embeddings for the Exploration of High-Dimensional Images
- URL: http://arxiv.org/abs/2602.24160v1
- Date: Fri, 27 Feb 2026 16:40:54 GMT
- Title: Manifold-Preserving Superpixel Hierarchies and Embeddings for the Exploration of High-Dimensional Images
- Authors: Alexander Vieth, Boudewijn Lelieveldt, Elmar Eisemann, Anna Vilanova, Thomas Höllt,
- Abstract summary: We present a superpixel hierarchy for high-dimensional images that takes the high-dimensional attribute manifold into account during construction.<n>Our method enables consistent exploration of high-dimensional images in both image and attribute space.
- Score: 44.208662556948106
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- Spatial Latent Representations in Generative Adversarial Networks for
Image Generation [0.0]
We define a family of spatial latent spaces for StyleGAN2.
We show that our spaces are effective for image manipulation and encode semantic information well.
arXiv Detail & Related papers (2023-03-25T20:01:11Z) - Diffusion and Volume Maximization-Based Clustering of Highly Mixed
Hyperspectral Images [5.16230883032882]
This article introduces the emphDiffusion and Volume-based Image Clustering (emphD-VIC) algorithm for unsupervised material discrimination.
D-VIC locates cluster modes -- high-density, high-purity pixels in the hyperspectral image that are far in diffusion distance from other high-density, high-purity pixels.
D-VIC upweights pixels that correspond to a spatial region containing just a single material, yielding more interpretable clusterings.
arXiv Detail & Related papers (2022-03-18T14:39:42Z) - Incorporating Texture Information into Dimensionality Reduction for
High-Dimensional Images [65.74185962364211]
We present a method for incorporating neighborhood information into distance-based dimensionality reduction methods.
Based on a classification of different methods for comparing image patches, we explore a number of different approaches.
arXiv Detail & Related papers (2022-02-18T13:17:43Z) - Decision boundaries and convex hulls in the feature space that deep
learning functions learn from images [0.0]
We study the properties of a low-dimensional manifold that models extract and learn from images.
For image classification models, their last hidden layer is the one where images of each class is separated from other classes and it also has the least number of features.
We observe that geometric arrangements of decision boundaries in feature space is significantly different compared to pixel space.
arXiv Detail & Related papers (2022-02-05T15:09:51Z) - Low-Rank Subspaces in GANs [101.48350547067628]
This work introduces low-rank subspaces that enable more precise control of GAN generation.
LowRankGAN is able to find the low-dimensional representation of attribute manifold.
Experiments on state-of-the-art GAN models (including StyleGAN2 and BigGAN) trained on various datasets demonstrate the effectiveness of our LowRankGAN.
arXiv Detail & Related papers (2021-06-08T16:16:32Z) - The Intrinsic Dimension of Images and Its Impact on Learning [60.811039723427676]
It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations.
In this work, we apply dimension estimation tools to popular datasets and investigate the role of low-dimensional structure in deep learning.
arXiv Detail & Related papers (2021-04-18T16:29:23Z) - Superpixel Segmentation Based on Spatially Constrained Subspace
Clustering [57.76302397774641]
We consider each representative region with independent semantic information as a subspace, and formulate superpixel segmentation as a subspace clustering problem.
We show that a simple integration of superpixel segmentation with the conventional subspace clustering does not effectively work due to the spatial correlation of the pixels.
We propose a novel convex locality-constrained subspace clustering model that is able to constrain the spatial adjacent pixels with similar attributes to be clustered into a superpixel.
arXiv Detail & Related papers (2020-12-11T06:18:36Z) - Free-Form Image Inpainting via Contrastive Attention Network [64.05544199212831]
In image inpainting tasks, masks with any shapes can appear anywhere in images which form complex patterns.
It is difficult for encoders to capture such powerful representations under this complex situation.
We propose a self-supervised Siamese inference network to improve the robustness and generalization.
arXiv Detail & Related papers (2020-10-29T14:46:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.