改进卷积网络结构，在CIFAR-10上达到84.95%准确率
Enhanced Convolutional Neural Networks for Improved Image Classification
- 引入更深的卷积块、批归一化和丢弃正则化
- 在CIFAR-10测试集上达84.95%准确率，优于基线模型
- 适合关注小规模图像分类优化的研究者
图像分类是计算机视觉中的基础任务，广泛应用于自动驾驶到医学影像等领域。CIFAR-10是评估小规模多类图像分类模型性能的常用基准数据集。卷积神经网络（CNN）虽已取得先进成果，但在如CIFAR-10等挑战性数据集上仍存在过拟合和特征表示不足的问题。本文提出一种增强型CNN架构，融合更深的卷积块、批归一化和丢弃正则化，以提升性能。该模型在测试集上达到84.95%的准确率，优于基准CNN架构。通过详细的消融实验，验证了各项改进的有效性，并分析了分层特征表示。本工作展示了优化后的CNN架构在小规模图像分类任务中的潜力。
原文摘要 · Abstract (English)
Image classification is a fundamental task in computer vision with diverse applications, ranging from autonomous systems to medical imaging. The CIFAR-10 dataset is a widely used benchmark to evaluate the performance of classification models on small-scale, multi-class datasets. Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art results; however, they often suffer from overfitting and suboptimal feature representation when applied to challenging datasets like CIFAR-10. In this paper, we propose an enhanced CNN architecture that integrates deeper convolutional blocks, batch normalization, and dropout regularization to achieve superior performance. The proposed model achieves a test accuracy of 84.95%, outperforming baseline CNN architectures. Through detailed ablation studies, we demonstrate the effectiveness of the enhancements and analyze the hierarchical feature representations. This work highlights the potential of refined CNN architectures for tackling small-scale image classification problems effectively.
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。