压缩模型可提升图像识别在真实噪声下的鲁棒性
Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
- 对ResNet-50等网络分别测试量化、剪枝、聚类及其组合
- 部分压缩策略使模型在CIFAR-10-C上准确率提升1.2%，鲁棒性增强
- 适合资源受限设备部署且需应对真实环境噪声的场景
压缩深度学习模型对在资源受限设备上部署视觉系统至关重要。然而，模型压缩可能影响其在自然退化下的鲁棒性。本文对卷积神经网络（ResNet-50、VGG-19、MobileNetV2）分别应用量化、剪枝和权重重聚，并组合使用，全面评估其对鲁棒性的影响。基于CIFAR-10-C与CIFAR 100-C数据集，分析了鲁棒性、准确率与压缩比之间的权衡。结果表明，某些压缩策略不仅能保持甚至提升鲁棒性，尤其在复杂架构中表现更优。通过多目标评估，确定了最优配置，证明定制化组合能实现多目标优化。本研究为在受污染现实环境中高效可靠部署模型提供了方法参考。
原文摘要 · Abstract (English)
Compressed deep learning models are crucial for deploying computer vision systems on resource-constrained devices. However, model compression may affect robustness, especially under natural corruption. Therefore, it is important to consider robustness evaluation while validating computer vision systems. This paper presents a comprehensive evaluation of compression techniques - quantization, pruning, and weight clustering applied individually and in combination to convolutional neural networks (ResNet-50, VGG-19, and MobileNetV2). Using the CIFAR-10-C and CIFAR 100-C datasets, we analyze the trade-offs between robustness, accuracy, and compression ratio. Our results show that certain compression strategies not only preserve but can also improve robustness, particularly on networks with more complex architectures. Utilizing multiobjective assessment, we determine the best configurations, showing that customized technique combinations produce beneficial multi-objective results. This study provides insights into selecting compression methods for robust and efficient deployment of models in corrupted real-world environments.
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。