Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions

TL;DR

This paper evaluates how different model compression techniques affect the robustness of CNNs against natural corruptions, revealing that some methods can enhance robustness while maintaining efficiency.

Contribution

It provides a comprehensive analysis of compression techniques' impact on CNN robustness under natural corruptions, highlighting optimal configurations for real-world deployment.

Findings

Certain compression methods improve robustness against corruptions

Complex architectures benefit more from specific compression strategies

Multi-objective assessment identifies optimal compression-robustness trade-offs

Abstract

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.