利用多任务学习与众包的特点以提高皮损诊断（Human-Computer Interaction）---用户6869393

人们认识到机器学习需要大量的带注释的数据。由于专家注释的高成本，群众外包，即要求非专家标记或轮廓图像，已被建议作为一种替代方案。虽然有许多有前途的结果被报道，诊断众包标签的质量仍然缺乏。我们建议通过向人群询问图像的视觉特征来解决这个问题，这些特征可以更直观地提供，并在一个多任务学习框架中使用这些特征。我们将我们提出的方法与基线模型进行比较，并与来自ISIC 2017挑战数据集的2000个皮肤损伤进行比较。基线模型仅从皮损图像预测一个二元标签，而我们的多任务模型还预测了以下特征之一:皮损的不对称性、边界不规则性和颜色。我们证明了群体特征与多任务学习相结合可以提高泛化能力。基线模型的接收机工作特性曲线下面积为0.754，有边框、有颜色、不对称的多任务模型下面积分别为0.785、0.786、0.787。最后，我们讨论了研究结果，确定了一些局限性，并提出了进一步研究的方向。

原文题目：Multi-task Learning with Crowdsourced Features Improves Skin Lesion Diagnosis

原文：Machine learning has a recognised need for large amounts of annotated data. Due to the high cost of expert annotations, crowd- sourcing, where non-experts are asked to label or outline images, has been proposed as an alternative. Although many promising results are reported, the quality of diagnostic crowdsourced labels is still lacking. We propose to address this by instead asking the crowd about visual features of the images, which can be provided more intuitively, and by using these features in a multi-task learning framework. We compare our proposed approach to a baseline model with a set of 2000 skin lesions from the ISIC 2017 challenge dataset. The baseline model only predicts a binary label from the skin lesion image, while our multi-task model also predicts one of the following features: asymmetry of the lesion, border irregularity and color. We show that crowd features in combination with multi-task learning leads to improved generalisation. The area under the receiver operating characteristic curve is 0.754 for the baseline model and 0.785, 0.786 and 0.787 for multi-task models with border, color and asymmetry respectively. Finally, we discuss the findings, identify some limitations and recommend directions for further research.

原文作者：Ralf Raumanns, Elif K Contar, Gerard Schouten, Veronika Cheplygina

原文链接：https://arxiv.org/abs/2004.14745