Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
By: Itallo Patrick Castro Alves Da Silva , Emanuel Adler Medeiros Pereira , Erick de Andrade Barboza and more
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.
Similar Papers
Model Compression vs. Adversarial Robustness: An Empirical Study on Language Models for Code
Software Engineering
Makes AI code checkers less safe when smaller.
From Code to Field: Evaluating the Robustness of Convolutional Neural Networks for Disease Diagnosis in Mango Leaves
Machine Learning (CS)
Makes AI better at spotting sick mango leaves.
Compressing CNN models for resource-constrained systems by channel and layer pruning
Machine Learning (CS)
Makes smart computer programs smaller and faster.