Seam Carving as Feature Pooling in CNN

TL;DR

This paper explores replacing max pooling in CNNs with seam carving, showing improved classification performance and better preservation of structural information in images.

Contribution

It introduces seam carving as a novel feature pooling method in CNNs, outperforming traditional max pooling in image classification tasks.

Findings

Seam carving-based CNN achieves higher accuracy.

Seam carving preserves more structural information.

Improved metrics like precision, recall, and F1-score.

Abstract

This work investigates the potential of seam carving as a feature pooling technique within Convolutional Neural Networks (CNNs) for image classification tasks. We propose replacing the traditional max pooling layer with a seam carving operation. Our experiments on the Caltech-UCSD Birds 200-2011 dataset demonstrate that the seam carving-based CNN achieves better performance compared to the model utilizing max pooling, based on metrics such as accuracy, precision, recall, and F1-score. We further analyze the behavior of both approaches through feature map visualizations, suggesting that seam carving might preserve more structural information during the pooling process. Additionally, we discuss the limitations of our approach and propose potential future directions for research.