通过双层比例约束提升弱监督标签预测精度
Learning from Label Proportions with Dual-proportion Constraints
- 在袋级和实例级同时施加比例约束，增强模型学习
- 使用最小费用最大流生成满足比例的伪标签，提升准确性
- 在多个数据集上优于现有方法，适合隐私敏感场景
学习从标签比例（LLP）是一种弱监督学习问题，训练数据以“袋子”形式存在，即一组实例，仅提供袋级类别比例标签，目标是学习一个能预测实例级标签的分类器。该设定在隐私限制无法获取实例级标注，或细粒度标注成本过高时具有广泛应用。本文提出一种基于双比例约束（LLP-DC）的方法，在训练中同时施加袋级与实例级的比例约束：袋级训练使预测均值匹配给定比例；实例级训练则通过最小费用最大流算法生成满足比例的硬伪标签，进一步约束模型输出。在多个基准数据集上的大量实验表明，LLP-DC在不同数据集和袋大小下均显著优于以往方法。代码已公开于 https://github.com/TianhaoMa5/CVPR2026_Findings_LLP_DC。
原文摘要 · Abstract (English)
Learning from Label Proportions (LLP) is a weakly supervised problem in which the training data comprise bags, that is, groups of instances, each annotated only with bag-level class label proportions, and the objective is to learn a classifier that predicts instance-level labels. This setting is widely applicable when privacy constraints limit access to instance-level annotations or when fine-grained labeling is costly or impractical. In this work, we introduce a method that leverages Dual proportion Constraints (LLP-DC) during training, enforcing them at both the bag and instance levels. Specifically, the bag-level training aligns the mean prediction with the given proportion, and the instance-level training aligns hard pseudo-labels that satisfy the proportion constraint, where a minimum-cost maximum-flow algorithm is used to generate hard pseudo-labels. Extensive experimental results across various benchmark datasets empirically validate that LLP-DC consistently improves over previous LLP methods across datasets and bag sizes. The code is publicly available at https://github.com/TianhaoMa5/CV PR2026_Findings_LLP_DC.
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。