Layer-Interaction Adaptive Pruning for Remote Sensing Scene Classification

The advancement of convolutional neural networks (CNNs) has enhanced remote sensing scene classification on satellites. However, the increased computational complexity of CNNs will impose a substantial burden on satellite hardware, thereby hindering the practical application. Although various pruning techniques have been developed to reduce the scale of CNNs by assessing the importance of model parameters, these weight-based methods are often accompanied by a degradation in model performance when the original model is undertrained and fails to provide meaningful parameters. In this article, we introduce a novel layer-interaction adaptive pruning (LiAP) method designed to streamline undertrained models. Unlike conventional approaches, LiAP evaluates the importance of neurons based on the distribution of eigenvalues rather than individual parameters. Specifically, this is achieved by projecting the weight matrix of each convolutional layer into the eigenspace, where the eigenvalues are utilized to assess the redundancy of filters. Then each space will be assigned a fined-score based on the eigenvalue distribution to provide a robust measure of filter importance. Compared to weight-based pruning methods, LiAP maintains consistent evaluation accuracy between well-trained and undertrained models, as the eigenspace is inherently robust to variations in the weight parameter space. We conducted extensive experiments on VGG-16 and ResNet-50 architectures using datasets such as AID, NWPU-RESISC45, PatternNet, and WHU-RS19 over various data partitions. Notably, our method achieved state-of-the-art (SOTA) reductions in both FLOPs and parameters for VGG-16 across the aforementioned datasets. These results underscore the efficacy of LiAP in enhancing the efficiency and applicability of CNNs in satellite-based remote sensing tasks.