XRFormer: Multiscale Tokenization for XRF Representation Learning

📄 arXiv: 2607.06424v1 📥 PDF

作者: Sofiane Daimellah, Sylvie Le Hégarat-Mascle, Clotilde Boust

分类: cs.CV

发布日期: 2026-07-07

备注: International Conference on Pattern Recognition, 2026

🔗 代码/项目: GITHUB

💡 一句话要点

提出XRFormer以解决XRF光谱自动学习挑战

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture)

关键词: XRF光谱 变换器架构 多尺度标记化 自监督学习 颜料识别 文化遗产分析 参数效率

📋 核心要点

  1. 现有的学习模型未能充分考虑XRF光谱中的复杂性，导致自动学习效果不佳。
  2. XRFormer通过多尺度卷积标记器设计，逐步降低光谱分辨率并增加嵌入维度，以适应XRF光谱特性。
  3. 在颜料识别和混合任务中，XRFormer在参数效率和性能上均显著优于现有基线模型。

📝 摘要（中文）

X射线荧光(XRF)光谱是文化遗产材料分析的重要手段，但从XRF光谱中进行自动学习仍然面临挑战。现有模型未能有效处理XRF光谱中的尖锐元素峰、宽结构和背景变化。本文提出XRFormer，一种针对XRF光谱的变换器架构，通过多尺度卷积标记器在全局自注意力之前注入局部性和多分辨率的归纳偏置。该标记器逐步降低光谱分辨率，同时增加嵌入维度，生成的标记序列由标准变换器编码器处理。实验结果表明，XRFormer在颜料识别和混合方面的表现优于现有模型，展示了多尺度、模态感知的标记化在数据有限条件下的有效性。

🔬 方法详解

问题定义：本文旨在解决从复杂的XRF光谱中进行自动学习的挑战，现有方法未能有效处理光谱中的尖锐峰值和背景变化，导致性能不足。

核心思路：XRFormer的核心思路是通过多尺度卷积标记器引入局部性和多分辨率的归纳偏置，逐步降低光谱分辨率并增加嵌入维度，以便更好地捕捉XRF光谱的特征。

技术框架：XRFormer的整体架构包括多尺度卷积标记器和标准变换器编码器。标记器负责将输入光谱转换为标记序列，随后由变换器编码器进行处理。

关键创新：XRFormer的主要创新在于其多尺度标记化方法，使得模型能够在数据有限的情况下有效学习XRF光谱的特征，与现有方法相比，显著提高了参数效率和性能。

关键设计：在设计中，XRFormer采用了Masked Spectral modeling (MSM)和Peak Presence Prediction (PPP)作为自监督预训练任务，优化了模型在颜料识别和混合任务中的表现。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，XRFormer在颜料识别任务中优于ViT和SpectralFormer，且在颜料混合任务中实现了更稳健的丰度估计。XRFormer在参数效率上表现突出，使用128个标记和150万参数，相较于SpectralFormer的512个标记和337万参数，显著降低了计算复杂度。

🎯 应用场景

该研究的潜在应用领域包括文化遗产材料分析、艺术品鉴定和环境监测等。通过提高XRF光谱的自动学习能力，XRFormer能够帮助研究人员更有效地识别和分析材料成分，推动相关领域的发展。

📄 摘要（原文）

X-ray fluorescence (XRF) spectroscopy is a key modality for material analysis in cultural heritage. However, automated learning from XRF spectra remains challenging: XRF spectra are complex one-dimensional signals composed of sharp elemental peaks, broader structures, and background variations that are not taken into account by existing learning-based models. This paper introduces XRFormer, a transformer architecture tailored to XRF spectra through a multiscale convolutional tokenizer that injects locality and multi-resolution inductive biases before global self-attention. The tokenizer progressively reduces spectral resolution while increasing embedding dimensionality, and the resulting token sequence is processed by a standard transformer encoder. We further investigate self-supervised pretraining for XRF representation learning using Masked Spectral modeling (MSM) and a physics-informed Peak Presence Prediction (PPP) objective. Experiments on the Pigments Checker STANDARD v.5 dataset for pigment identification and unmixing show that XRFormer consistently outperforms ViT, SpectralFormer (with and without CAF), and a 1D-CNN baseline for pigment identification. For pigment unmixing, XRFormer achieves robust abundance estimation while maintaining significantly higher parameter efficiency than SpectralFormer, operating at a lower token resolution (128 vs. 512 tokens) and with less than half the number of parameters (1.5M vs. 3.37M). MSM yields consistent gains across both tasks, while PPP further enhances performance for both identification and unmixing when tuned with an appropriate peak prominence. These results highlight multiscale, modality-aware tokenization as an effective and parameter efficient foundation for transformer-based XRF modeling under data-limited conditions. A GitHub repository is provided at https://github.com/sofiane1010/XRFormer.