An Effective Instance-Level Contrastive Training Strategy for Ship Detection in SAR Images | IEEE Journals & Magazine | IEEE Xplore

An Effective Instance-Level Contrastive Training Strategy for Ship Detection in SAR Images


Abstract:

Existing ship detection approaches in SAR images often suffer from inadequate learning of the detector and suboptimal detection performance. To this end, based on self-su...Show More

Abstract:

Existing ship detection approaches in SAR images often suffer from inadequate learning of the detector and suboptimal detection performance. To this end, based on self-supervised contrastive learning, this letter considers using the relationship between samples to develop a more effective training strategy. First, the instance-based region of interest (RoI) encode head is proposed, named InsRen head, a simple yet effective network structure. Its purpose is to encode the samples into a contrastive feature space, facilitating the measurement of contrastive learning. Furthermore, to adapt contrastive learning to ship detection, we have redefined some basic terms, such as query, positive key, and negative key, which can help the model build the training pipeline. Finally, we design the instance-based contrastive loss that does not require label supervision, named InsCon loss. With the penalty of the InsCon loss, the queries and positive key can learn more similar representations in the contrastive feature space. Simultaneously, the query and negative key are as far away as possible to increase the difference. With the help of InsRen head and InsCon loss, the training of the detection model is more effective. Experimental results demonstrate the superiority of our method.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 20)
Article Sequence Number: 4007505
Date of Publication: 12 July 2023

ISSN Information:

Funding Agency:


References

References is not available for this document.