ABSTRACT Underwater images harbor abundant resources for marine science and applications. The fusion of Transformers and CNNs has emerged as a promising approach for salient object detection. These encoders extract hierarchical features at different scales, each exhibiting unique characteristics. Low‐level features primarily focus on detailed information, whereas deep features encapsulate higher level semantic information. Motivated by these observations, we design a hierarchical fusion network combining the Swin Transformer with a CNN for underwater salient object detection. Underwater images are preprocessed via an enhancement algorithm utilised to restore attenuated spectral characteristics. At the low‐level encoder stages, global features derived from the Swin Transformer and local features extracted from ResNet50 are integrated via an adaptive interactive fusion strategy, which prioritises detail preservation. At the high‐level encoder stages, long‐range dependency features are aggregated with local features via a cross‐attention fusion module, which emphasises semantic interaction. An upsampling and fusion decoder is designed to generate a coarse saliency map, densely integrating the hierarchical features while preserving fine details. Finally, a post‐refinement network is utilised to further enhance detection performance by leveraging boundary and contextual information, achieving an accurate salient object segmentation result. Experimental results demonstrate that our method achieves F ‐measure scores of 0.9322, 0.9247, and 0.8332 on the USOD10K, USOD, and UFO‐120 datasets, highlighting the efficacy of hierarchical fusion of Swin Transformer and CNN for underwater salient object detection. The code of our method is available at https://github.com/leckie711/hfusod .
Huang et al. (Thu,) studied this question.