Few-shot Semantic Segmentation by Exploiting Dynamic and Regional Contexts

Hongyu Gu, Yunzhi Zhuge, Lu Zhang, Jinqing Qi, Huchuan Lu

Abstract: Few-shot Semantic Segmentation (FSS) has received increasing interests recently. Modeling effective interaction be-tween support and query images is a crucial challenge in existing prototype based methods. In this paper, we propose a Dynamic and Regional Context Network (DRCNet) to achieve sufficient support-query interaction for accurate FSS. A Dynamic Context Module (DCM) is first proposed to capture the spatial details in query images by building dynamic convolutions in local views. To further alleviate the undesirable noises, a Regional Context Module (RCM) is proposed to mine and exclude the background and ambiguous objects in query images by modeling the prototypes for ambiguous regions. Experimental results on Pascal-5 i and COCO-20 i datasets demonstrate that our proposed DRCNet performs significantly superior against state-of-the-art methods.