GroupSeg: An Efficient Grouping Transformer Network for Polyp Segmentation

Mingwen Zhang, Haiying Xia, Yumei Tan

Abstract: Precise polyp segmentation is extremely challenging due to the diverse appearances and shaps’s of polyps along with severe light imbalance. To this end, we propose a novel network architecture, GroupSeg, which aims to learn robust representations by fully exploring global contextual representations and texture features of polyps through grouping segmentation to improve polyp segmentation performance. Specifically, GroupSeg groups features from the transformer encoder into progressively larger segments of different shapes, making full use of global contextual information to generate segmentation maps from fine to coarse, and thus can automatically adapt to polyps of different shapes and sizes, and is highly adaptive to the distribution of different polyp datasets. To further mine texture features to improve the performance of polyp segmentation, we introduce a Grouping Feature Aggregation Module (GFA), which adaptively mines the clues of local pixels and grouping feature segments, making the grouping features more accurate.GroupSeg demonstrates superior performance compared to state-of-the-art methods on ETIS, Endoscene, and ColonDB datasets, while high competitiveness on ClinicDB. It offers propsective outcomes in polyp segmentation.