Multi-Objective Net Architecture Pruning for Remote Sensing Classification

Remote sensing image scene classification has achieved significant breakthroughs in recent years. However, due to the high complexity and expensive computation most of CNNs used in the field of remote sensing imagery scene classification, it has become a challenging task for extracting effective features at restricted hardware conditions. To solve this problem, we present a model compression method by means of evolutionary algorithms. Specifically, we compress the model by pruning filters and transform the compression of the CNN model into a multi-objective optimization problem based on classification accuracy and compression ratio by using the adaptive-BN-based evaluation method. Furthermore, the prior knowledge of ResNet-50 on ImageNet is introduced to reduce the instability of evolutionary algorithm as a result of random population initialization. Experiments are implemented on three datasets with two evolutionary algorithms, and results demonstrate that our method can achieve state-of-the-art performances.