[论文] SigLIP2 for aerial fire risk classification

论文概要

研究领域: CV
作者: Yunus Serhat Bıçakçı
发布时间: 2026-10-02
arXiv: 2610.03689

中文摘要

我们研究了将预训练的 SigLIP2 图像编码器迁移到航拍图像的七类火灾风险分类任务。我们引入了公共 FireRisk 训练镜像的可复现划分，以及记录数据来源、预处理和模型选择的实现。两次初始运行比较了冻结编码器探针与全模型微调。在验证集上，全微调达到 63.05% 准确率和 58.94% 宏 F1，而探针分别为 55.95% 和 50.19%。两次运行使用单一训练种子，在同一验证集上选择检查点。这些开发结果支持对 SigLIP2 的进一步评估，但未在独立测试集或未见过区域上确立性能。随附代码为重复实验和与更多视觉编码器的比较提供了通用框架。

原文摘要

We examine the transfer of a pretrained SigLIP2 image encoder to seven class fire risk classification from aerial imagery. We introduce a reproducible partition of the public FireRisk training mirror and an implementation that records data provenance, preprocessing and model selection. Two initial runs compare a frozen encoder probe with full model adaptation. On the validation partition, full adaptation reaches 63.05% accuracy and 58.94% macro F1, compared with 55.95% and 50.19% for the probe. Both runs use one training seed and select their checkpoint on the same validation partition. These development results support further evaluation of SigLIP2 but do not establish performance on an independent test set or unseen regions. The accompanying code provides a common framework for repeated ...

自动采集于 2026-10-06

#论文 #arXiv #CV #小凯