Toward Efficient Power Scene Detection via Topology-Preserved Knowledge Distillation
Yi, Junfei Liu, Tengfei Mao, Jianxu Wang, Yaonan Zhang, Hui Xie, He Zhong, Hang Chang, Xiaojun
Yi, Junfei
Liu, Tengfei
Mao, Jianxu
Wang, Yaonan
Zhang, Hui
Xie, He
Zhong, Hang
Chang, Xiaojun
Supervisor
Department
Computer Vision
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The power industry relies on efficient inspection systems to ensure stability and safety. While deep learning has advanced automated inspection, its reliance on custom modules for specific tasks can impact efficiency. Knowledge distillation (KD) offers a balanced solution, but the complex textures and structures of power equipment challenge conventional KD methods, which often fail to capture essential local semantic and topological relationships. To address this, we propose TopNet, a novel topology-preserved KD framework for power scene detection tasks. Specifically, we model the teacher’s knowledge as a graph, where nodes encode local fine-grained features and edges capture global topological relationships. Based on this, we introduce node feature distillation and edge feature distillation to transfer local–global structural knowledge, which can enhance the student’s ability to perceive objects. Furthermore, we also introduce aggregated feature distillation to incorporate and transfer contextual semantic knowledge. Comprehensive experiments are conducted on two different benchmark datasets to demonstrate that TopNet achieves state-of-the-art detection performance with high efficiency, offering a robust solution for automated power equipment inspection.
Citation
J. Yi et al., "Toward Efficient Power Scene Detection via Topology-Preserved Knowledge Distillation," in IEEE Transactions on Industrial Informatics, doi: 10.1109/TII.2025.3588592
Source
IEEE Transactions on Industrial Informatics
Conference
Keywords
Automated Inspection, Graph Representation, Knowledge Distillation (KD), Power Equipment Detection, Topology Preservation
Subjects
Source
Publisher
IEEE