通过实验消融优化CNN，提升CIFAR-10分类准确率
Empirical Ablation and Ensemble Optimization of a Convolutional Neural Network for CIFAR-10 Classification
- 系统测试17种训练与结构修改，找出有效改进
- 最佳组合达89.23%准确率，优于单一模型
- 强调实证选择比盲目加深网络更有效
卷积神经网络（CNN）在图像分类中仍占核心地位，但其性能高度依赖架构与训练策略。本文针对CIFAR-10基准进行基于消融的实证研究，评估了17种渐进式修改，包括训练时长、学习率调度、丢弃率配置、池化策略、网络深度、滤波器排列及全连接层设计。基线模型测试准确率为79.5%。延长训练时间稳步提升性能，而多项结构重设计虽增加复杂度却降低准确率。基于表现最优的独立配置构建加权集成模型，在数据缩减设置下达到86.38%准确率，全数据集训练下达89.23%。结果表明，CNN分类性能提升不依赖于盲目加深或增参，而取决于对训练与架构调整的谨慎实证选择。研究凸显了消融导向优化与集成学习在小图像分类中的实用价值。
原文摘要 · Abstract (English)
Convolutional neural networks (CNNs) remain a central approach in image classification, but their performance depends strongly on architectural and training choices. This paper presents an empirical ablation-based study of CNN optimization for the CIFAR-10 benchmark. The study evaluates 17 progressive modifications involving training duration, learning-rate scheduling, dropout configuration, pooling strategy, network depth, filter arrangement, and dense-layer design. The goal is to identify which changes improve generalization and which increase complexity without improving performance. The baseline model achieved 79.5\% test accuracy. Extending training duration improved performance steadily, whereas several structural redesigns reduced accuracy despite greater architectural variation. Based on the strongest individual configurations, a weighted ensemble was constructed, achieving 86.38\% accuracy in the reduced-data setting and 89.23\% when trained using the full CIFAR-10 dataset. These results suggest that performance gains in CNN-based classification depend less on indiscriminate increases in depth or parameter count than on careful empirical selection of training and architectural modifications. The study therefore highlights the practical value of ablation-oriented optimization and ensemble learning for small-image classification.
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。