HiImp-SMI:An Implicit Transformer Framework with High-Frequency Adapter for Medical Image Segmentation

Huang LianchaoFeng Peng^*Binghao HuangYinghong Cao^*

• Dalian Polytechnic University, Dalian, China

In this paper, an implicit transformer framework with a high-frequency adapter for medical image segmentation (HiImp-SMI) is proposed. A new dual-branch architecture is designed to simultaneously process spatial and frequency information, enhancing both boundary refinement and domain adaptability. Specifically, a Channel Attention Block selectively amplifies highfrequency boundary cues, improving contour delineation. A Multi-Branch Cross-Attention Block facilitates efficient hierarchical feature fusion, addressing challenges in multi-scale representation. Additionally, a ViT-Conv Fusion Block adaptively integrates global contextual awareness from Transformer features with local structural details, thereby significantly boosting crossdomain generalization. Experimental evaluations show that HiImp-SMI consistently outperforms mainstream models on the Kvasir-Sessile and BCV datasets, including state-of-the-art implicit methods. These quantitative results demonstrate the framework's effectiveness in refining boundary precision, optimizing multi-scale feature representation, and improving cross-dataset generalization.