PDF(Pubmed)
Abstract：
Due to the difficulty in obtaining clinical samples and the high cost of labeling, rare skin diseases are characterized by data scarcity, making training deep neural networks for classification challenging. In recent years, few-shot learning has emerged as a promising solution, enabling models to recognize unseen disease classes by limited labeled samples. However, most existing methods ignored the fine-grained nature of rare skin diseases, resulting in poor performance when generalizing to highly similar classes. Moreover, the distributions learned from limited labeled data are biased, severely impairing the model\'s generalizability. This paper proposes a self-supervision distribution calibration network (SS-DCN) to address the above issues. Specifically, SS-DCN adopts a multi-task learning framework during pre-training. By introducing self-supervised tasks to aid in supervised learning, the model can learn more discriminative and transferable visual representations. Furthermore, SS-DCN applied an enhanced distribution calibration (EDC) strategy, which utilizes the statistics of base classes with sufficient samples to calibrate the bias distribution of novel classes with few-shot samples. By generating more samples from the calibrated distribution, EDC can provide sufficient supervision for subsequent classifier training. The proposed method is evaluated on three public skin disease datasets(i.e., ISIC2018, Derm7pt, and SD198), achieving significant performance improvements over state-of-the-art methods.
摘要：
由于临床样本获取困难，标签成本高，罕见皮肤病的特点是数据稀缺，使得训练深度神经网络进行分类具有挑战性。近年来,少量学习已经成为一种有希望的解决方案，使模型能够通过有限的标记样本识别未发现的疾病类别。然而,大多数现有方法忽略了罕见皮肤病的细粒度性质，导致在推广到高度相似的类时性能较差。此外，从有限的标记数据中学习到的分布是有偏差的，严重损害模型的泛化性。针对上述问题,提出了一种自监督分布校准网络(SS-DCN)。具体来说,SS-DCN在预训练期间采用多任务学习框架。通过引入自我监督任务来帮助监督学习，该模型可以学习更多的辨别性和可转移的视觉表示。此外，SS-DCN应用了增强的分布校准(EDC)策略，它利用具有足够样本的基类的统计信息来校准具有少量样本的新类的偏差分布。通过从校准的分布中产生更多的样本，EDC可以为后续分类器训练提供足够的监督。所提出的方法在三个公共皮肤病数据集上进行了评估(即，ISIC2018,Derm7pt,和SD198），与最先进的方法相比，实现了显著的性能改进。
