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 2008.08416cs.CVcs.LGeess.IV
收藏

弱监督主动学习在乳腺超声图像肿块检测中的逐步应用

Gradually Applying Weakly Supervised and Active Learning for Mass Detection in Breast Ultrasound Images

Korea University(高丽大学);Hankik University of Foreign Studies(韩国外国语大学)

JooYeol Yun, JungWoo Oh, IlDong Yun

摘要:

我们提出了一种方法,有效地利用弱注释的图像数据中的乳房超声图像的目标检测任务。给定其中小的、强注释的数据集和没有限界框信息的大的、弱注释的数据集可用的问题设置,训练目标检测模型变成非平凡问题。我们提出了一个控制的权重,用于处理两阶段目标检测模型中弱注释图像的影响。我们还提出了一个后续的主动学习计划,安全地分配弱注释图像使用训练模型的强注释。实验结果表明,通过分配适当控制的权重,正确定位(CorLoc)的措施,这是正确定位和分类的图像的比率增加了24点。在训练模型后执行主动学习显示CorLoc的额外增加。我们在Stanford Dog数据集上测试了所提出的方法,以确保它可以应用于一般情况,其中强注释不足以获得类似的结果。所提出的方法表明,更高的性能是实现较少的注释工作。

英文摘要:

We propose a method for effectively utilizing weakly annotated image data in an object detection tasks of breast ultrasound images. Given the problem setting where a small, strongly annotated dataset and a large, weakly annotated dataset with no bounding box information are available, training an object detection model becomes a non-trivial problem. We suggest a controlled weight for handling the effect of weakly annotated images in a two stage object detection model. We~also present a subsequent active learning scheme for safely assigning weakly annotated images a strong annotation using the trained model. Experimental results showed a 24\% point increase in correct localization (CorLoc) measure, which is the ratio of correctly localized and classified images, by assigning the properly controlled weight. Performing active learning after a model is trained showed an additional increase in CorLoc. We tested the proposed method on the Stanford Dog datasets to assure that it can be applied to general cases, where strong annotations are insufficient to obtain resembling results. The presented method showed that higher performance is achievable with lesser annotation effort.

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。

↑