Wang Bei, He Bing, Li Chao, Shen Xiaowei, Zhang Xianyang
School of Nuclear Engineering, PLA Rocket Force University of Engineering, Xi'an, 710025, China.
Department of Basic Courses, PLA Rocket Force University of Engineering, Xi'an, 710025, China.
Sci Rep. 2025 Mar 18;15(1):9329. doi: 10.1038/s41598-025-93072-8.
The challenge of enhancing the detection accuracy of widely adopted and stable object detectors while maintaining cost-effectiveness has long been a topic of significant interest and concern within the industry. To address this challenge, this paper proposes a general relation-based self-distillation framework suitable for object detection to help existing detectors achieve a better balance between accuracy and overhead. Compared to existing self-distillation methods, the framework we propose focuses on integrating relation-based knowledge into the self-distillation framework. To achieve this goal, we propose a relation-based self-distillation method within the framework and design a targeted optimization strategy in the form of an adaptive filtering strategy. The relation-based self-distillation method constrains the detector from focusing on the differences in the representation of the same type of object in different scenarios; and the adaptive filtering strategy filters the low-confidence results predicted by the detector before calling the matching mechanism, thereby ensuring the efficiency of the training process. A large number of experimental results show that our method can significantly improve the accuracy of existing detectors and reduce their redundant prediction results without increasing the computational resource overhead of existing detectors.
在保持成本效益的同时提高广泛采用且稳定的目标检测器的检测精度，长期以来一直是该行业中备受关注的重要话题。为应对这一挑战，本文提出了一种适用于目标检测的基于关系的通用自蒸馏框架，以帮助现有检测器在精度和开销之间实现更好的平衡。与现有的自蒸馏方法相比，我们提出的框架专注于将基于关系的知识集成到自蒸馏框架中。为实现这一目标，我们在框架内提出了一种基于关系的自蒸馏方法，并以自适应滤波策略的形式设计了一种有针对性的优化策略。基于关系的自蒸馏方法限制检测器关注不同场景中同一类型对象表示的差异；而自适应滤波策略在调用匹配机制之前对检测器预测的低置信度结果进行滤波，从而确保训练过程的效率。大量实验结果表明，我们的方法可以在不增加现有检测器计算资源开销的情况下，显著提高现有检测器的精度并减少其冗余预测结果。
