Positional Relation Contextual Mixing for Imbalanced Classification

doi:10.1007/s10994-026-07004-2

Positional Relation Contextual Mixing for Imbalanced Classification

2026-03-06

0

PRE

AI

DOI：10.1007/s10994-026-07004-2

Original

Original request for help

Save

Abstract

En 中文

In practical applications, datasets often exhibit imbalanced distributions. Deep models trained on imbalanced data frequently produce biased results, leading to degraded generalization performance. Data augmentation techniques represent a key approach to addressing imbalanced data. Although random image class mixing is widely regarded as a reliable method, existing mix-based augmentation strategies often neglect the spatial relationships between majority and minority class images, potentially generating low-quality samples. In this paper, we adopt an optimal transport approach to perform pre-matching based on the spatial relationships between primary objects across images before class mixing. This method ensures the accuracy of primary object positioning for both majority and minority classes while maximizing the utilization of majority-class background images. Experimental results demonstrate that as a data-centric input-level optimization method, our approach achieves superior performance across various imbalanced scenarios and exhibits scalability.

Keywords:

Imbalanced

Mix

Positional

Optimal transport

Positional Relation Contextual Mixing for Imbalanced Classification

Abstract

Journal

Organization