Online Decoupled Distillation Based on Prototype Contrastive Learning for Lightweight Underwater Object Detection Models
IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-14
DOI: 10.1109/tgrs.2025.3549129 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Xiao Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: Natural Science Foundation of Science and Technology Department of Shaanxi Province, Key Project of National Natural Science Foundation of China.
Abstract (Originalsprache)
Underwater object detection tasks face significant challenges due to the complexity of aquatic environments and underwater conditions, coupled with the limited computational resources of current underwater equipment. The characteristics of online knowledge distillation, including its ability to compress models and enhance the performance and generalization capability of lightweight models, make it a highly suitable approach for underwater object detection tasks. Despite this, the key parameter setting of online knowledge distillation is still challenging in underwater image object detection, because of the difficulties in capturing the key information that differentiates different underwater objects. Therefore, we propose an online decoupled distillation framework based on prototype contrastive learning (PCD). The core idea of PCD is to facilitate knowledge transfer among a group of networks through prototype contrastive learning and to design decoupled distillation to enable the student model to learn more comprehensive and fine-grained knowledge. In the PCD model, we employ a contrastive loss to align the distributions of the student model and the teacher model in the feature space, enhancing its semantic structural properties. This enables the student model to achieve better feature representation. Innovatively, we use the average feature vector as the prototype to execute prototype contrastive learning to ensure model stability, thereby enhancing the detection capability of lightweight models in complex environments. On detectors, we designed cross-knowledge transfer and decoupled distillation loss to make the distillation of the logit output more comprehensive and effective. Our extensive experimental results demonstrate significant improvements in underwater object detection tasks and applicability to various types of dense detectors. Our PCD can improve the average precision of ResNet-based GFL detectors by 3.0–5.3, proving the effectiveness of our PCD model.
Förderung
- Natural Science Foundation of Science and Technology Department of Shaanxi Province
- Key Project of National Natural Science Foundation of China
Zitieren
APA
Chen, X., Chen, X., Ge, X., Chen, J., & Wang, H. (2025). Online Decoupled Distillation Based on Prototype Contrastive Learning for Lightweight Underwater Object Detection Models. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-14. https://doi.org/10.1109/tgrs.2025.3549129
Vancouver
Chen X, Chen X, Ge X, Chen J, Wang H. Online Decoupled Distillation Based on Prototype Contrastive Learning for Lightweight Underwater Object Detection Models. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-14. doi:10.1109/tgrs.2025.3549129
BibTeX
@article{Chen2025,
author = {Chen, Xiao and Chen, Xingwu and Ge, Xiaoqi and Chen, Jiayi and Wang, Haiyan},
title = {Online Decoupled Distillation Based on Prototype Contrastive Learning for Lightweight Underwater Object Detection Models},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
year = {2025},
volume = {63},
pages = {1--14},
doi = {10.1109/tgrs.2025.3549129}
}
EUVIMED