通过元组件组合提升少样本学习泛化能力
Toward Better Generalization in Few-Shot Learning through the Meta-Component Combination
- 将分类器拆解为可复用的元组件，跨任务学习共享结构
- 在多个基准测试中优于现有方法，显著提升未见类识别效果
- 适合需要强泛化能力的少样本场景，如医疗图像识别
少样本学习要求分类器在仅提供少量新类别样本的情况下实现泛化。主流方案是基于度量的元学习，但其严重依赖在已见类别上学习的深度度量，容易过拟合于已见类别，难以泛化到未见类别。为此，本文探索分类器的子结构，提出一种新型元学习算法，将每个分类器建模为元组件的组合。元组件在已见类别的元学习轮次中联合学习，并通过正交正则化强制解耦，以提升多样性并捕捉不同分类器间的共享子结构。在多个少样本基准任务上的实验表明，该方法性能显著优于现有方法。
原文摘要 · Abstract (English)
In few-shot learning, classifiers are expected to generalize to unseen classes given only a small number of instances of each new class. One of the popular solutions to few-shot learning is metric-based meta-learning. However, it highly depends on the deep metric learned on seen classes, which may overfit to seen classes and fail to generalize well on unseen classes. To improve the generalization, we explore the substructures of classifiers and propose a novel meta-learning algorithm to learn each classifier as a combination of meta-components. Meta-components are learned across meta-learning episodes on seen classes and disentangled by imposing an orthogonal regularizer to promote its diversity and capture various shared substructures among different classifiers. Extensive experiments on few-shot benchmark tasks show superior performances of the proposed method.
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。