发表机构
United International University; American International University Bangladesh; ELITE Research Lab, New York, USA（联合国际大学; 孟加拉美国国际大学; ELITE研究实验室（纽约，美国））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无人机图像分割中采集泄露问题，提出采集感知评估协议，在杂草稻数据集上验证了采集暴露对性能的影响及模态排名依赖架构，强调同测试评估的必要性。
AI 中文摘要
无人机图像采集包含空间和时间上相关的帧，然而语义分割基准通常以图像级别进行划分。这种划分方式可能将来自同一采集的样本同时置于模型开发和测试中，从而掩盖了对全新调查的泛化能力。利用包含734个样本的WeedyRice-RGBMS-DB数据集，我们固定了一个包含124张图像的目标采集测试集，并比较了两种具有相同训练、验证和测试数量的协议：目标排除协议（在开发过程中排除目标采集）和目标暴露协议（允许使用目标采集的其余图像）。使用RGB、四波段多光谱（MS）和七通道RGB+MS输入，在两种固定划分种子下评估SegFormer-B0。在完全采集排除下，RGB表现最强（IoU为0.7317±0.0201），而在目标暴露后，RGB+MS成为最强（IoU为0.7822±0.0269）。使用固定划分的U-Net/ResNet18进行复现，确认了所有三种输入在暴露后均有正向增益，但两种协议下RGB仍是最佳模态。因此，采集暴露提高了两种评估骨干网络的测量性能，而其对手模态排名的影响则依赖于架构。提供的划分审计揭示了强烈的近序列依赖性，而损坏测试表明，早期融合对RGB-MS位移的敏感性远高于对中等辐射缩放的敏感性。这些结果支持将采集感知的同测试评估作为多模态无人机基准中普通图像级划分的必要补充。支持本研究发现的代码和材料将在论文被接收后公开发布。
英文摘要
UAV image collections contain spatially and temporally related frames, yet semantic-segmentation benchmarks commonly split them at image level. Such splitting can place samples from one acquisition in both model development and testing, obscuring transfer to a genuinely new survey. Using the 734-sample WeedyRice-RGBMS-DB, we fix a 124-image target-acquisition test set and compare two protocols with identical train, validation, and test counts: target-held-out, which excludes the target acquisition from development, and target-exposed, which admits its remaining images. SegFormer-B0 is evaluated with RGB, four-band multispectral (MS), and seven-channel RGB+MS input over two fixed-split seeds. RGB is strongest under complete acquisition holdout ($0.7317\pm0.0201$ IoU), whereas RGB+MS becomes strongest after target exposure ($0.7822\pm0.0269$). A fixed-split U-Net/ResNet18 replication confirms positive exposure gains for all three inputs, but retains RGB as the best modality under both protocols. Acquisition exposure therefore increases measured performance across both evaluated backbones, while its effect on modality ranking is architecture-dependent. A supplied-split audit reveals strong near-sequential dependence, and corruption tests show that early fusion is substantially more sensitive to RGB--MS displacement than to moderate radiometric scaling. These results support acquisition-aware same-test evaluation as a necessary complement to ordinary image-level splitting in multimodal UAV benchmarks. The code and supporting the findings of this study will be publicly released upon acceptance of the paper.
