Multi-scale constraints and perturbation consistency for semi-supervised sonar image segmentation

Emerging semi-supervised learning methods have enabled great progress in segmentation tasks. However, popular semi-supervised segmentation models use constraints that are not strict. In this paper, we propose a new method, multi-scale cross pseudo-supervision, that introduces higher constraints by multi-scale information to improve the quality of pseudo-labels. Specifically, we extend the backbone segmentation network by adding a multi-scale feature pyramid at the decoder to extract multi-scale information. In addition, to further enhance the consistency on multiple scales, we perform perturbation operations on the original input image. Experiments show that our method achieves excellent segmentation performance on both sonar and ISIC2016 datasets. The performance gain benefits from two techniques—multi-scale constraints and perturbation consistency. And the proposed method alleviates the annotation pressure for image segmentation in real-world human-centric applications.