Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
This work addresses the problem of ensuring robustness in compressed deep learning models for deployment on resource-constrained devices, though it is incremental as it focuses on evaluation rather than introducing new methods.
This paper evaluated how compression techniques like quantization, pruning, and weight clustering affect the robustness of CNNs under natural corruptions, finding that some strategies can preserve or even improve robustness, especially in complex architectures, with results analyzed on CIFAR-10-C and CIFAR-100-C datasets.
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.