Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2601.12715 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912831977291776 |
|---|---|
| author | Li, Chengzhou Guo, Ping Meng, Guanchen Jia, Qi Liu, Jinyuan Liu, Zhu Liu, Xiaokang Liu, Yu Luo, Zhongxuan Fan, Xin |
| author_facet | Li, Chengzhou Guo, Ping Meng, Guanchen Jia, Qi Liu, Jinyuan Liu, Zhu Liu, Xiaokang Liu, Yu Luo, Zhongxuan Fan, Xin |
| contents | Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-experts to distinguish subtle differences between classes. This leads to their inability to provide precise annotation data for sonar images. Therefore, designing effective object detection methods for sonar images with extremely limited labels is particularly important. To address this, we propose a teacher-student framework called RSOD, which aims to fully learn the characteristics of sonar images and develop a pseudo-label strategy suitable for these images to mitigate the impact of limited labels. First, RSOD calculates a reliability score by assessing the consistency of the teacher's predictions across different views. To leverage this score, we introduce an object mixed pseudo-label method to tackle the shortage of labeled data in sonar images. Finally, we optimize the performance of the student by implementing a reliability-guided adaptive constraint. By taking full advantage of unlabeled data, the student can perform well even in situations with extremely limited labels. Notably, on the UATD dataset, our method, using only 5% of labeled data, achieves results that can compete against those of our baseline algorithm trained on 100% labeled data. We also collected a new dataset to provide more valuable data for research in the field of sonar. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12715 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels Li, Chengzhou Guo, Ping Meng, Guanchen Jia, Qi Liu, Jinyuan Liu, Zhu Liu, Xiaokang Liu, Yu Luo, Zhongxuan Fan, Xin Computer Vision and Pattern Recognition Artificial Intelligence Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-experts to distinguish subtle differences between classes. This leads to their inability to provide precise annotation data for sonar images. Therefore, designing effective object detection methods for sonar images with extremely limited labels is particularly important. To address this, we propose a teacher-student framework called RSOD, which aims to fully learn the characteristics of sonar images and develop a pseudo-label strategy suitable for these images to mitigate the impact of limited labels. First, RSOD calculates a reliability score by assessing the consistency of the teacher's predictions across different views. To leverage this score, we introduce an object mixed pseudo-label method to tackle the shortage of labeled data in sonar images. Finally, we optimize the performance of the student by implementing a reliability-guided adaptive constraint. By taking full advantage of unlabeled data, the student can perform well even in situations with extremely limited labels. Notably, on the UATD dataset, our method, using only 5% of labeled data, achieves results that can compete against those of our baseline algorithm trained on 100% labeled data. We also collected a new dataset to provide more valuable data for research in the field of sonar. |
| title | RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.12715 |