RSAFormer: A method of polyp segmentation with region self-attention transformer

Xuehui Yin, Jun Zeng, Tianxiao Hou, Chao Tang, Chenquan Gan, Deepak Kumar Jain, Salvador García

Abstract: Highlights•A region self-attention enhancement network (RSAFormer) is proposed.•RSAFormer uniquely uses a dual decoder structure to generate various feature maps.•A novel region self-attention enhancement (RSA) module is proposed.