Double Reverse Regularization Network Based on Self-Knowledge Distillation for SAR Object Classification
This addresses overfitting in SAR object classification for remote sensing applications, but it is incremental as it builds on existing self-knowledge distillation methods.
The paper tackles severe overfitting in synthetic aperture radar (SAR) object classification due to limited and noisy data by proposing a Double Reverse Regularization Network based on Self-Knowledge Distillation (DRRNet-SKD), which outperforms state-of-the-art self-knowledge distillation methods on OpenSARShip and FUSAR-Ship datasets.
In current synthetic aperture radar (SAR) object classification, one of the major challenges is the severe overfitting issue due to the limited dataset (few-shot) and noisy data. Considering the advantages of knowledge distillation as a learned label smoothing regularization, this paper proposes a novel Double Reverse Regularization Network based on Self-Knowledge Distillation (DRRNet-SKD). Specifically, through exploring the effect of distillation weight on the process of distillation, we are inspired to adopt the double reverse thought to implement an effective regularization network by combining offline and online distillation in a complementary way. Then, the Adaptive Weight Assignment (AWA) module is designed to adaptively assign two reverse-changing weights based on the network performance, allowing the student network to better benefit from both teachers. The experimental results on OpenSARShip and FUSAR-Ship demonstrate that DRRNet-SKD exhibits remarkable performance improvement on classical CNNs, outperforming state-of-the-art self-knowledge distillation methods.