Multi-Instance Partial-Label Learning with Margin Adjustment

TL;DR

This paper introduces MIPLMA, a novel algorithm for multi-instance partial-label learning that adjusts margins for attention scores and predicted probabilities, leading to improved generalization over existing methods.

Contribution

The paper proposes a margin-aware attention mechanism and a margin distribution loss to enhance multi-instance partial-label learning performance.

Findings

MIPLMA outperforms existing MIPL algorithms in experiments.

The margin adjustment improves classification accuracy.

The approach enhances generalization in multi-instance partial-label learning.

Abstract

Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overlook the margins for attention scores and predicted probabilities, leading to suboptimal generalization performance. A critical issue with these algorithms is that the highest prediction probability of the classifier may appear on a non-candidate label. In this paper, we propose an algorithm named MIPLMA, i.e., Multi-Instance Partial-Label learning with Margin Adjustment, which adjusts the margins for attention scores and predicted probabilities. We introduce a margin-aware attention mechanism to dynamically adjust the margins for attention scores and propose a margin distribution loss to constrain the margins between the predicted probabilities on candidate and non-candidate label sets. Experimental results demonstrate the superior performance of MIPLMA over existing MIPL algorithms, as well as other well-established multi-instance learning algorithms and partial-label learning algorithms.