Deep Global Clustering for Hyperspectral Image Segmentation: Concepts, Applications, and Open Challenges

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Yu-Tang, Chen, Pin-Wei, Chen, Shih-Fang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912797029302272
author Chang, Yu-Tang
Chen, Pin-Wei
Chen, Shih-Fang
author_facet Chang, Yu-Tang
Chen, Pin-Wei
Chen, Shih-Fang
contents Hyperspectral imaging (HSI) analysis faces computational bottlenecks due to massive data volumes that exceed available memory. While foundation models pre-trained on large remote sensing datasets show promise, their learned representations often fail to transfer to domain-specific applications like close-range agricultural monitoring where spectral signatures, spatial scales, and semantic targets differ fundamentally. This report presents Deep Global Clustering (DGC), a conceptual framework for memory-efficient HSI segmentation that learns global clustering structure from local patch observations without pre-training. DGC operates on small patches with overlapping regions to enforce consistency, enabling training in under 30 minutes on consumer hardware while maintaining constant memory usage. On a leaf disease dataset, DGC achieves background-tissue separation (mean IoU 0.925) and demonstrates unsupervised disease detection through navigable semantic granularity. However, the framework suffers from optimization instability rooted in multi-objective loss balancing: meaningful representations emerge rapidly but degrade due to cluster over-merging in feature space. We position this work as intellectual scaffolding - the design philosophy has merit, but stable implementation requires principled approaches to dynamic loss balancing. Code and data are available at https://github.com/b05611038/HSI_global_clustering.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24172
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Global Clustering for Hyperspectral Image Segmentation: Concepts, Applications, and Open Challenges
Chang, Yu-Tang
Chen, Pin-Wei
Chen, Shih-Fang
Computer Vision and Pattern Recognition
Machine Learning
68T05, 68T10, 62H30
I.4.6; I.5.3; I.2.6
Hyperspectral imaging (HSI) analysis faces computational bottlenecks due to massive data volumes that exceed available memory. While foundation models pre-trained on large remote sensing datasets show promise, their learned representations often fail to transfer to domain-specific applications like close-range agricultural monitoring where spectral signatures, spatial scales, and semantic targets differ fundamentally. This report presents Deep Global Clustering (DGC), a conceptual framework for memory-efficient HSI segmentation that learns global clustering structure from local patch observations without pre-training. DGC operates on small patches with overlapping regions to enforce consistency, enabling training in under 30 minutes on consumer hardware while maintaining constant memory usage. On a leaf disease dataset, DGC achieves background-tissue separation (mean IoU 0.925) and demonstrates unsupervised disease detection through navigable semantic granularity. However, the framework suffers from optimization instability rooted in multi-objective loss balancing: meaningful representations emerge rapidly but degrade due to cluster over-merging in feature space. We position this work as intellectual scaffolding - the design philosophy has merit, but stable implementation requires principled approaches to dynamic loss balancing. Code and data are available at https://github.com/b05611038/HSI_global_clustering.
title Deep Global Clustering for Hyperspectral Image Segmentation: Concepts, Applications, and Open Challenges
topic Computer Vision and Pattern Recognition
Machine Learning
68T05, 68T10, 62H30
I.4.6; I.5.3; I.2.6
url https://arxiv.org/abs/2512.24172