PFDE-DCN: A Lightweight Class Incremental Learning Method for Radar HRRP Recognition

Deep neural networks have been widely used in the field of high-resolution range profile (HRRP) radar automatic target recognition (RATR) and have achieved promising results. However, when a new target class appears, how the deep neural networks learn new knowledge and update the model is still an emerging problem. Directly using the new target class samples to train the deep neural networks will cause the problem of “catastrophic forgetting.” In this article, we propose a two-stage distillation learning method, PFDE-DCN, to solve the HRRP class incremental learning (CIL) problem. First, we use a machine learning boosting algorithm to dynamically extend the network and a pooled distillation learning algorithm to enable knowledge migration between the old and new feature extraction networks. Then, we use the distillation learning method to compress the extended network. The distillation strategy keeps the critical network parameters and removes the redundant network parameters to avoid the infinite increase of model complexity. We conduct experiments on both simulated and measured aircraft HRRP datasets, and the experimental results show that our method PFDE-DCN obtains the state-of-the-art performance.