Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks. However, high computational and storage demands hinder their deployment into resource-constrained environments, such as embedded devices. Model pruning helps to meet these restrictions by reducing the model size, while maintaining superior performance. Meanwhile, safety-critical applications pose more than just resource and performance constraints. In particular, predictions must not be overly confident, i.e., provide properly calibrated uncertainty estimations (proper uncertainty calibration), and CNNs must be robust against corruptions like naturally occurring input perturbations (natural corruption robustness). This work investigates the important trade-off between uncertainty calibration, natural corruption robustness, and performance for current state-of-research post-hoc CNN pruning techniques in the context of image classification tasks. Our study reveals that post-hoc pruning substantially improves the model's uncertainty calibration, performance, and natural corruption robustness, sparking hope for safe and robust embedded CNNs.Furthermore, uncertainty calibration and natural corruption robustness are not mutually exclusive targets under pruning, as evidenced by the improved safety aspects obtained by post-hoc unstructured pruning with increasing compression.

翻译：卷积神经网络（CNN）在许多计算机视觉任务中已取得最先进的性能。然而，高计算与存储需求阻碍了其在资源受限环境（如嵌入式设备）中的部署。模型剪枝通过减小模型规模来满足这些限制，同时保持优异性能。与此同时，安全关键型应用所提出的要求不仅限于资源与性能约束。具体而言，预测结果不应过度自信，即需提供恰当校准的不确定性估计（适当的不确定性校准），且CNN必须对诸如自然发生的输入扰动等干扰具有鲁棒性（自然干扰鲁棒性）。本研究在图像分类任务背景下，探讨了当前研究前沿的后剪枝CNN技术中不确定性校准、自然干扰鲁棒性与性能之间的重要权衡关系。我们的研究表明，后剪枝能显著提升模型的不确定性校准、性能及自然干扰鲁棒性，这为安全且鲁棒的嵌入式CNN带来了希望。此外，在剪枝条件下，不确定性校准与自然干扰鲁棒性并非互斥目标，这一点通过后剪枝非结构化剪枝随压缩率增加而获得的安全性能提升得到了证实。