---
title: "Many Pixels, One Composition: Self-Supervised Spectra for Specimen-Level Prediction"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06096v1"
permalink: "https://feed.astralor.com/items/itm_ccabc9cc867bcb6c6915f3c7"
published: "2026-11-04T07:42:25.000Z"
score: 56
channel: "ai"
tags: ["Many Pixels","One Composition","Self-Supervised Spectra","Specimen-Level Prediction Can","Earth","Can"]
---

# Many Pixels, One Composition: Self-Supervised Spectra for Specimen-Level Prediction

## 速览

Can hyperspectral (HS) imaging be used to predict the elemental composition of physical specimens found on the Earth's surface? We approach this problem as a supervised regression task, using an open dataset of specimen…

## 关键点

- Can hyperspectral (HS) imaging be used to predict the elemental composition of physical specimens found on the Earth's surface?
- We approach this problem as a supervised regression task, using an open dataset of specimens, each comprising a HS cube and elemental characterization.
- In particular, we train an encoder in a self-supervised fashion that operates on pixel-level; then freeze the encoder and train a lightweight attention-based regression head in a supervised manner, by pairing many repre…

## 全文

Can hyperspectral (HS) imaging be used to predict the elemental composition of physical specimens found on the Earth's surface? We approach this problem as a supervised regression task, using an open dataset of specimens, each comprising a HS cube and elemental characterization. In particular, we train an encoder in a self-supervised fashion that operates on pixel-level; then freeze the encoder and train a lightweight attention-based regression head in a supervised manner, by pairing many representations of a given specimen with its corresponding elemental label. In test specimens, our approach significantly outperforms traditional spectral matching and unmixing baselines. It also outperforms supervised learning models based on the mean spectrum (of similar model capacity), while full model fine-tuning achieves the strongest performance, at substantially higher model capacity.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_ccabc9cc867bcb6c6915f3c7