Semantic segmentation of underwater images based on the improved SegFormer

Underwater images segmentation is essential for tasks such as underwater exploration, marine environmental monitoring, and resource development. Nevertheless, given the complexity and variability of the underwater environment, improving model accuracy remains a key challenge in underwater image segmentation tasks. To address these issues, this study presents a high-performance semantic segmentation approach for underwater images based on the standard SegFormer model. First, the Mix Transformer backbone in SegFormer is replaced with a Swin Transformer to enhance feature extraction and facilitate efficient acquisition of global context information. Next, the Efficient Multi-scale Attention (EMA) mechanism is introduced in the backbone’s downsampling stages and the decoder to better capture multi-scale features, further improving segmentation accuracy. Furthermore, a Feature Pyramid Network (FPN) structure is incorporated into the decoder to combine feature maps at multiple resolutions, allowing the model to integrate contextual information effectively, enhancing robustness in complex underwater environments. Testing on the SUIM underwater image dataset shows that the proposed model achieves high performance across multiple metrics: mean Intersection over Union (MIoU) of 77.00%, mean Recall (mRecall) of 85.04%, mean Precision (mPrecision) of 89.03%, and mean F1score (mF1score) of 86.63%. Compared to the standard SegFormer, it demonstrates improvements of 3.73% in MIoU, 1.98% in mRecall, 3.38% in mPrecision, and 2.44% in mF1score, with an increase of 9.89M parameters. The results demonstrate that the proposed method achieves superior segmentation accuracy with minimal additional computation, showcasing high performance in underwater image segmentation.