arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.18279cs.CVcs.LG
收藏

通过置信度评估改进地球观测基础模型以增强语义分割

Improving EO Foundation Models with Confidence Assessment for enhanced Semantic segmentation

European Space Agency (ESA)(欧洲空间局(ESA))

Nikolaos Dionelis, Nicolas Longepe

AI总结:

本文提出CAS模型,通过片段级和像素级组合置信度度量识别错误预测片段并精化模型,在Sentinel-2土地覆盖分类等地球观测语义分割任务中优于基线模型。

摘要:

语义分割算法的置信度评估非常重要。理想情况下,深度学习模型应具备提前预测其输出是否可能错误的能力。在地球观测(EO)分类中评估模型预测的置信水平至关重要,因为它可以增强语义分割性能,并有助于在预测错误时防止对结果的进一步利用。我们开发的模型——用于增强语义分割的置信度评估(CAS)——在片段级和像素级两个层面评估置信度,同时输出标签和置信度分数。我们的模型CAS利用所提出的组合置信度度量来识别预测标签不正确的片段,对模型进行精化,并提升其性能。这项工作具有重要应用价值,特别是在评估地球观测基础模型在语义分割下游任务上的表现方面,例如使用Sentinel-2卫星数据进行土地覆盖分类。评估结果表明该策略是有效的,并且所提出的模型CAS优于其他基线模型。

英文摘要:

Confidence assessments of semantic segmentation algorithms are important. Ideally, deep learning models should have the ability to predict in advance whether their output is likely to be incorrect. Assessing the confidence levels of model predictions in Earth Observation (EO) classification is essential, as it can enhance semantic segmentation performance and help prevent further exploitation of the results in case of erroneous prediction. The model we developed, Confidence Assessment for enhanced Semantic segmentation (CAS), evaluates confidence at both the segment and pixel levels, providing both labels and confidence scores as output. Our model, CAS, identifies segments with incorrect predicted labels using the proposed combined confidence metric, refines the model, and enhances its performance. This work has significant applications, particularly in evaluating EO Foundation Models on semantic segmentation downstream tasks, such as land cover classification using Sentinel-2 satellite data. The evaluation results show that this strategy is effective and that the proposed model CAS outperforms other baseline models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑