Data augmentation by morphological mixup for solving Raven's Progressive Matrices

TL;DR

This paper introduces CAM-Mix, a morphological mixup data augmentation technique for RPM datasets that improves model generalization and accuracy by creating semantically similar negative answers.

Contribution

The paper proposes CAM-Mix, a novel morphological mixup method that enhances RPM solution models by regularizing training and improving decision boundaries.

Findings

Significant performance improvements on RPM datasets.

Enhanced model generalization and reduced overfitting.

Effective creation of semantically similar negative answers.

Abstract

Raven's Progressive Matrices (RPMs) are frequently used in testing human's visual reasoning ability. Recent advances of RPM-like datasets and solution models partially address the challenges of visually understanding the RPM questions and logically reasoning the missing answers. In view of the poor generalization performance due to insufficient samples in RPM datasets, we propose an effective scheme, namely Candidate Answer Morphological Mixup (CAM-Mix). CAM-Mix serves as a data augmentation strategy by gray-scale image morphological mixup, which regularizes various solution methods and overcomes the model overfitting problem. By creating new negative candidate answers semantically similar to the correct answers, a more accurate decision boundary could be defined. By applying the proposed data augmentation method, a significant and consistent performance improvement is achieved on various RPM-like datasets compared with the state-of-the-art models.