# Tree-based Semantic Losses: Application to Sparsely-supervised Large Multi-class Hyperspectral Segmentation

Source: [Tree-based Semantic Losses: Application to Sparsely-supervised Large Multi-class Hyperspectral Segmentation](<https://www.sota2.com/research/paper/68fa7be61e209131cea8b2a9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T11:00:18.583Z

Authors: Junwen Wang, Oscar Maccormac, William Rochford, Aaron Kujawa, Jonathan Shapey, Tom Vercauteren

Published: 2025-06-26T11:20:46.000Z

## Abstract

Hyperspectral imaging (HSI) shows great promise for surgical applications, offering detailed insights into biological tissue differences beyond what the naked eye can perceive. Refined labelling efforts are underway to train vision systems to distinguish large numbers of subtly varying classes. However, commonly used learning methods for biomedical segmentation tasks penalise all errors equivalently and thus fail to exploit any inter-class semantics in the label space. In this work, we introduce two tree-based semantic loss functions which take advantage of a hierarchical organisation of the labels. We further incorporate our losses in a recently proposed approach for training with sparse, background-free annotations. Extensive experiments demonstrate that our proposed method reaches state-of-the-art performance on a sparsely annotated HSI dataset comprising $107$ classes organised in a clinically-defined semantic tree structure. Furthermore, our method enables effective detection of out-of-distribution (OOD) pixels without compromising segmentation performance on in-distribution (ID) pixels.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.21150>)

[PDF](<https://arxiv.org/pdf/2506.21150.pdf>)
