Guardado en:
Detalles Bibliográficos
Autor principal: Jubair, Mohammad Imrul
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2409.06311
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912020879638528
author Jubair, Mohammad Imrul
author_facet Jubair, Mohammad Imrul
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_06311
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Seam Carving as Feature Pooling in CNN
Jubair, Mohammad Imrul
Computer Vision and Pattern Recognition
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.
title Seam Carving as Feature Pooling in CNN
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.06311