基于自知识蒸馏的双反向正则化网络用于SAR目标分类
Double Reverse Regularization Network Based on Self-Knowledge Distillation for SAR Object Classification
AI总结：
针对SAR目标分类中的过拟合问题，提出基于自知识蒸馏的双反向正则化网络DRRNet-SKD，结合离线与在线蒸馏并设计自适应权重分配模块，显著提升了分类性能。
摘要：
在当前的合成孔径雷达（SAR）目标分类中，由于数据集受限（few-shot）和噪声数据导致的严重过拟合问题是主要挑战之一。考虑到知识蒸馏作为学习到的标签平滑正则化的优势，本文提出了一种基于自知识蒸馏的新型双反向正则化网络（DRRNet-SKD）。具体而言，通过探索蒸馏权重对蒸馏过程的影响，我们受到启发采用双反向思想，以互补的方式结合离线和在线蒸馏，构建了有效的正则化网络。随后，设计了自适应权重分配（AWA）模块，基于网络性能自适应地分配两个反向变化的权重，使学生网络能更好地从两个教师网络中获益。在OpenSARShip和FUSAR-Ship上的实验结果表明，DRRNet-SKD在经典CNN上表现出显著的性能提升，优于当前最先进的自知识蒸馏方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
