Underwater object detection is of great value in marine resource development, but the traditional fully supervised methods are limited due to the scarcity of labeled data. Currently, semi-supervised learning is an efficient approach to addressing this issue. However, the complex underwater environment may exacerbate issues such as pseudo-label noise, bias, and insufficient feature extraction in traditional semi-supervised methods. To address these issues, we propose an innovative framework for underwater semi-supervised object detection. Firstly, we design a CARAFE-enhanced PAFPN (CE-PAFPN) model that can solve the problem of high-level features lacking low-level details in FPN while fully integrating contextual information and improving the model’s ability to learn target features. Secondly, we propose an adaptive threshold adjustment mechanism to mitigate the pseudo-label noise, which dynamically adjusts the threshold to filter high-quality pseudo-labels according to the sample difficulty. Finally, by incorporating a class-balance loss to downweight overly confident pseudo-labels, thereby mitigating the pseudo-label bias caused by class imbalance. The proposed method ultimately achieves 56.8% \(mAP_{50:95}\) on the DUO dataset with only 10% labeled data, outperforming the baseline SoftTeacher by 3.1%. Additionally, comparative results on the DUO and URPC public datasets reveal that our method outperforms existing semi-supervised object detection methods under different semi-supervised settings.