A high-precision underwater object detection based on joint self-supervised deblurring and improved spatial transformer network
This work addresses degraded visibility and insufficient training data in underwater object detection, offering a domain-specific solution with incremental improvements.
The paper tackled the challenge of underwater object detection by proposing a method that combines self-supervised deblurring and an improved spatial transformer network, achieving 47.9 mAP on URPC2017 and 70.3 mAP on URPC2018, outperforming state-of-the-art methods.
Deep learning-based underwater object detection (UOD) remains a major challenge due to the degraded visibility and difficulty to obtain sufficient underwater object images captured from various perspectives for training. To address these issues, this paper presents a high-precision UOD based on joint self-supervised deblurring and improved spatial transformer network. A self-supervised deblurring subnetwork is introduced into the designed multi-task learning aided object detection architecture to force the shared feature extraction module to output clean features for detection subnetwork. Aiming at alleviating the limitation of insufficient photos from different perspectives, an improved spatial transformer network is designed based on perspective transformation, adaptively enriching image features within the network. The experimental results show that the proposed UOD approach achieved 47.9 mAP in URPC2017 and 70.3 mAP in URPC2018, outperforming many state-of-the-art UOD methods and indicating the designed method is more suitable for UOD.