Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning

2025-09-04

AI Summary

This paper introduces “Majority-Class Label Learning,” a novel multi-instance learning (MIL) paradigm that trains instance-level classifiers using only bag-level majority-class labels—without requiring precise instance-level annotations. To address this challenge, we propose the Counting Network to explicitly model the per-class instance counts within each bag. We further design the Majority Proportion Enhancement Module (MPEM), which employs a differentiable proportion-based enhancement mechanism to strengthen discriminability for the majority class. Additionally, we integrate instance selection with gradient back-propagation to refine the estimation of intra-bag class distributions. Extensive experiments on four benchmark datasets demonstrate substantial improvements over state-of-the-art MIL methods. Ablation studies confirm the effectiveness and necessity of each component. The source code is publicly available.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Multiagent Systems: Multiagent Learning
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The paper proposes a novel multi-class Multiple-Instance Learning (MIL) problem called Learning from Majority Label (LML). In LML, the majority class of instances in a bag is assigned as the bag-level label. The goal of LML is to train a classification model that estimates the class of each instance using the majority label. This problem is valuable in a variety of applications, including pathology image segmentation, political voting prediction, customer sentiment analysis, and environmental monitoring. To solve LML, we propose a Counting Network trained to produce bag-level majority labels, estimated by counting the number of instances in each class. Furthermore, analysis experiments on the characteristics of LML revealed that bags with a high proportion of the majority class facilitate learning. Based on this result, we developed a Majority Proportion Enhancement Module (MPEM) that increases the proportion of the majority class by removing minority class instances within the bags. Experiments demonstrate the superiority of the proposed method on four datasets compared to conventional MIL methods. Moreover, ablation studies confirmed the effectiveness of each module. The code is available at href{https://github.com/Shiku-Kaito/Learning-from-Majority-Label-A-Novel-Problem-in-Multi-class-Multiple-Instance-Learning}{here}.

Problem

• Learning instance classification from bag-level majority labels
• Estimating individual instance classes using majority labels
• Enhancing majority class proportion for improved learning

Innovation

• Counting Network estimates bag-level majority labels
• Majority Proportion Enhancement Module removes minority instances
• Method improves multi-class multiple-instance learning performance