论文标题
微调的预训练的蒙版R-CNN模型用于表面对象检测
Fine-tuned Pre-trained Mask R-CNN Models for Surface Object Detection
论文作者
论文摘要
这项研究使用四个蒙版R-CNN模型评估道路表面对象检测任务，作为石制考古物体的表面劣化检测的预研究。这些模型经过可可数据集和15,188个分段的路面注释标签进行了预训练和微调。使用平均精度和平均召回量测量模型的质量。结果表明，假阴性的数量大量计数，即左检测和未分类的检测。测试了一个修改的混淆矩阵模型以避免优先考虑IOU，并且在边界框检测中有显着的正面增加，但几乎没有分割掩模的变化。
This study evaluates road surface object detection tasks using four Mask R-CNN models as a pre-study of surface deterioration detection of stone-made archaeological objects. The models were pre-trained and fine-tuned by COCO datasets and 15,188 segmented road surface annotation tags. The quality of the models were measured using Average Precisions and Average Recalls. Result indicates substantial number of counts of false negatives, i.e. left detection and unclassified detections. A modified confusion matrix model to avoid prioritizing IoU is tested and there are notable true positive increases in bounding box detection, but almost no changes in segmentation masks.
