用缝合裁剪替代传统池化，提升图像分类性能
Seam Carving as Feature Pooling in CNN
- 以缝合裁剪代替最大池化，保留更多图像结构信息
- 在鸟类数据集上准确率、F1等指标全面优于传统模型
- 适合关注特征保留与图像结构的视觉任务研究者
本文探讨将缝合裁剪（seam carving）作为卷积神经网络中特征池化技术的潜力，用于图像分类任务。我们提出用缝合裁剪操作替代传统的最大池化层。在Caltech-UCSD Birds 200-2011数据集上的实验表明，基于缝合裁剪的CNN在准确率、精确率、召回率和F1分数等指标上均优于使用最大池化的模型。通过特征图可视化分析，我们发现缝合裁剪在池化过程中可能更好地保留了图像的结构信息。同时，论文也讨论了该方法的局限性，并提出了未来的研究方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。