发表机构
University of Limerick（利默里克大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出半自动步长无关补丁（SSP）替代步长依赖补丁技术，构建三类补丁数据集训练DeepLabV3+模型，发现SSP在分割性能与训练时间间平衡更优。
AI 中文摘要
本文提出半自动步长无关补丁（SSP），作为自动步长依赖补丁技术的替代方案。SSP利用用户或专家输入，将预定义补丁定位在一个或多个感兴趣对象上。为评估其有效性，使用SSP、重叠补丁（Overlap）和非重叠补丁（Noverlap）创建了三个基于补丁的数据集。分别在每个数据集上训练带有ResNet50、ResNet18和MobileNetV2骨干的DeepLabV3+模型，在各自的测试集和一个通用外部测试集上进行定量评估。SSP在各自测试集上通常获得更高的分割分数，且在所有三个骨干中所需的模型训练时间最短；在外部测试集上，SSP在各骨干中获得最高的平均精度和F1分数，而Noverlap获得最高的平均召回率。这些初步结果表明，Noverlap和Overlap潜在更大的空间覆盖范围通常并未转化为更好的分割性能，SSP在分割性能与模型训练时间之间提供了良好的平衡。
英文摘要
This paper presents semi-automatic stride-independent patching (SSP) as an alternative to automatic stride-dependent patching techniques. SSP uses user or expert input to position predefined patches over one or more objects of interest. To evaluate its effectiveness, three patch-based datasets were created using SSP, overlapping patching (Overlap), and non-overlapping patching (Noverlap). DeepLabV3+ models with ResNet50, ResNet18, and MobileNetV2 backbones were trained sepa-rately on each dataset. Quantitative evaluations were performed on the respective test splits and a common external test set. SSP generally achieved higher segmentation scores on the test splits and required the shortest model training time across all three backbones. On the external test set, SSP achieved the highest average precision and F1-score across backbones, whereas Noverlap achieved the highest average recall. These preliminary results demonstrate that the potentially greater spatial coverage of Noverlap and Overlap does not generally translate into better segmentation perfor-mance and that SSP offers a favorable balance between segmentation performance and model training time.
Comments8 pages, 6 figures, 2 tables
