收藏切换
Cross-Label Assignment Knowledge Distillation Based End-to-End Object Detection
收藏切换
Zhiliang Hu1, 2, Si Chen1, 2, *, Dahan Wang1, 2, Yan Yan3
Journal of Computer Research and Development | 2026, 63(10) : 2682 - 2696
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(10): 2682-2696
• Artificial Intelligence •
Cross-Label Assignment Knowledge Distillation Based End-to-End Object Detection
Full
Zhiliang Hu1, 2, Si Chen1, 2, *, Dahan Wang1, 2, Yan Yan3
Affiliations
  • 1School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, Fujian 361024
  • 2Fujian Key Laboratory of Pattern Recognition and Image Understanding (Xiamen University of Technology), Xiamen, Fujian 361024
  • 3School of Informatics, Xiamen University, Xiamen, Fujian 361100
  • born in 1999. Master candidate. His main research interests include computer vision and object detection

    born in 1987. PhD, professor, master supervisor. Her main research interests include computer vision, machine learning, and pattern recognition

    born in 1983. PhD, professor, master supervisor. His main research interests include pattern recognition, text detection and recognition, and semantic segmentation

    born in 1984. PhD, professor, PhD supervisor. His main research interests include computer vision and pattern recognition

About Author:

born in 1999. Master candidate. His main research interests include computer vision and object detection

born in 1987. PhD, professor, master supervisor. Her main research interests include computer vision, machine learning, and pattern recognition

born in 1983. PhD, professor, master supervisor. His main research interests include pattern recognition, text detection and recognition, and semantic segmentation

born in 1984. PhD, professor, PhD supervisor. His main research interests include computer vision and pattern recognition

Published: 2026-10-01 doi: 10.7544/issn1000-1239.202550737
Outline
收藏切换

Recently, the one-to-one label assignment rule has played a great role in removing non-maximum suppression (NMS) in the post-processing step and building an NMS-free end-to-end detection paradigm. However, this strict sample matching rule leads to a significant reduction in the number of positive samples during the training process, making it difficult for the model to fully mine the latent semantic information in the data during the feature representation learning stage, resulting in low learning efficiency. To this end, we propose a cross-label assignment knowledge distillation (CAKD) method for end-to-end object detection. This method combines the transfer learning mechanism of knowledge distillation with the end-to-end object detection algorithm to make up for the defects of the existing one-to-one label assignment rule and establishes an effective knowledge transfer path for the knowledge distillation framework to train end-to-end detection models. Specifically, the multi-scale features of the student model are first transferred to the detection head of the teacher model across models. Then, the student-teacher cross-label assignment predictions are compared with the teacher’s predictions to calculate the distillation loss. This method avoids directly forcing the student to imitate the teacher’s features, which leads to feature confusion and semantic misalignment. In addition, we also design an effective task-aware matching metric that comprehensively considers the quality of classification and regression, thus avoiding the problem of irrelevance between classification and localization tasks. We conduct a large number of experiments on COCO dataset to demonstrate the effectiveness of this method. By applying the cross-label assignment knowledge distillation method proposed in this paper to the non-end-to-end FCOS baseline model, it achieves a 38.8% non-NMS detection performance in terms of mean average precision (mAP), which is a 2.2 percentage point accuracy gain compared with the original detection performance with NMS.

end-to-end object detection  /  NMS-free detection  /  knowledge distillation  /  cross-label assignment  /  computer vision
胡志良, 陈思, 王大寒, 严严. 基于跨标签分配知识蒸馏的端到端目标检测方法. 计算机研究与发展, 2026 , 63 (10) : 2682 -2696 . DOI: 10.7544/issn1000-1239.202550737
Zhiliang Hu, Si Chen, Dahan Wang, Yan Yan. Cross-Label Assignment Knowledge Distillation Based End-to-End Object Detection[J]. Journal of Computer Research and Development, 2026 , 63 (10) : 2682 -2696 . DOI: 10.7544/issn1000-1239.202550737
Year 2026 volume 63 Issue 10
104
50
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550737
  • Receive Date:2025-10-14
  • Online Date:2026-11-17
  • Published:2026-10-01
Article Data
Affiliations
History
  • Received:2025-10-14
  • Revised:2026-04-28
  • Accepted:2026-05-14
Affiliations
    1School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, Fujian 361024
    2Fujian Key Laboratory of Pattern Recognition and Image Understanding (Xiamen University of Technology), Xiamen, Fujian 361024
    3School of Informatics, Xiamen University, Xiamen, Fujian 361100
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550737
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT