用预训练模型实现皮肤疾病分类的持续学习，不遗忘旧知识。
Foundation Models as Class-Incremental Learners for Dermatological Image Classification
- 冻结主干网络，仅训练轻量MLP逐步学习新疾病类别。
- 在多个数据集上超越现有方法，实现零遗忘且性能领先。
- 无需微调，用原型匹配也能达到良好效果，适合医疗场景。
类增量学习（CIL）旨在不遗忘已有知识的前提下，逐步学习新类别。大型皮肤病变数据集预训练的基础模型（FM）提供了丰富的可迁移表征，为皮肤病分类中的增量学习带来新机遇。本文系统评估了冻结的FM在皮肤疾病分类中的表现，提出一种简单有效的方法：保持主干网络不变，仅对每个任务增量训练一个轻量级MLP。该方法在不遗忘的情况下实现当前最优性能，优于正则化、重放和结构改进等方法。为进一步探索冻结FM的能力，我们考察了零训练场景下，基于嵌入特征原型的最近均值分类器。通过大量消融实验，证明该原型方法同样具备竞争力。结果表明，冻结基础模型在医学持续学习中具有强大潜力，支持其在真实医疗应用中的推广。代码与数据集已公开。
原文摘要 · Abstract (English)
Class-Incremental Learning (CIL) aims to learn new classes over time without forgetting previously acquired knowledge. The emergence of foundation models (FM) pretrained on large datasets presents new opportunities for CIL by offering rich, transferable representations. However, their potential for enabling incremental learning in dermatology remains largely unexplored. In this paper, we systematically evaluate frozen FMs pretrained on large-scale skin lesion datasets for CIL in dermatological disease classification. We propose a simple yet effective approach where the backbone remains frozen, and a lightweight MLP is trained incrementally for each task. This setup achieves state-of-the-art performance without forgetting, outperforming regularization, replay, and architecture based methods. To further explore the capabilities of frozen FMs, we examine zero training scenarios using nearest mean classifiers with prototypes derived from their embeddings. Through extensive ablation studies, we demonstrate that this prototype based variant can also achieve competitive results. Our findings highlight the strength of frozen FMs for continual learning in dermatology and support their broader adoption in real world medical applications. Our code and datasets are available here.
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。