用代表性样本选数据，让皮肤病变分割在少标注下更准
An Attentive Representative Sample Selection Strategy Combined with Balanced Batch Training for Skin Lesion Segmentation
- 通过原型对比学习选最具代表性的图像用于标注
- 在低标注预算下，分割精度显著优于现有方法
- 适合数据标注成本高的医学图像任务
医疗图像分割研究中常被忽视的问题是：如何从大量未标注数据中有效选择训练子集进行标注。许多研究采用随机采样，可能导致模型性能不佳，尤其在极小标注预算下，每张图的影响尤为显著。本文提出一种结合原型对比学习与聚类的样本选择策略，提取具有代表性和多样性的样本。同时引入无监督均衡批次加载机制，提升小规模标注数据下的模型学习效果。在公开皮肤病变数据集ISIC 2018上评估，相较于当前最优采样方法，本方法在低标注预算下表现更优。
原文摘要 · Abstract (English)
An often overlooked problem in medical image segmentation research is the effective selection of training subsets to annotate from a complete set of unlabelled data. Many studies select their training sets at random, which may lead to suboptimal model performance, especially in the minimal supervision setting where each training image has a profound effect on performance outcomes. This work aims to address this issue. We use prototypical contrasting learning and clustering to extract representative and diverse samples for annotation. We improve upon prior works with a bespoke cluster-based image selection process. Additionally, we introduce the concept of unsupervised balanced batch dataloading to medical image segmentation, which aims to improve model learning with minimally annotated data. We evaluated our method on a public skin lesion dataset (ISIC 2018) and compared it to another state-of-the-art data sampling method. Our method achieved superior performance in a low annotation budget scenario.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。