用高斯混合模型分析卷积神经网络滤波器，揭示过拟合机制。
Explaining Model Overfitting in CNNs via GMM Clustering
- 通过GMM聚类特征图，识别异常滤波器。
- 发现异常滤波器与过拟合显著相关。
- 适用于AlexNet、LeNet-5等主流架构，无需修改。
卷积神经网络（CNN）在计算机视觉领域表现出色，但其决策过程缺乏可解释性，制约了实际应用。本文提出一种基于高斯混合模型（GMM）的量化评估方法，对模型中各滤波器对应的特征图进行聚类分析，识别出与异常样本相关的异常滤波器。进一步研究了异常滤波器与模型过拟合之间的关系，提出了三个假设，并通过三组精心设计的实验，从模型行为、数据集特性及滤波器影响三个角度验证。该方法无需修改即可适用于多种CNN架构，如AlexNet和LeNet-5。本工作为评估CNN性能提供了新视角，深化了对过拟合行为的理解。
原文摘要 · Abstract (English)
Convolutional Neural Networks (CNNs) have demonstrated remarkable prowess in the field of computer vision. However, their opaque decision-making processes pose significant challenges for practical applications. In this study, we provide quantitative metrics for assessing CNN filters by clustering the feature maps corresponding to individual filters in the model via Gaussian Mixture Model (GMM). By analyzing the clustering results, we screen out some anomaly filters associated with outlier samples. We further analyze the relationship between the anomaly filters and model overfitting, proposing three hypotheses. This method is universally applicable across diverse CNN architectures without modifications, as evidenced by its successful application to models like AlexNet and LeNet-5. We present three meticulously designed experiments demonstrating our hypotheses from the perspectives of model behavior, dataset characteristics, and filter impacts. Through this work, we offer a novel perspective for evaluating the CNN performance and gain new insights into the operational behavior of model overfitting.
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。