Contour and Enclosed Region Refining for Contour-Based Instance Segmentation

Current contour-based instance segmentation methods predict sets of vertexes to form contours to enclose object instances in images for realizing instance segmentation. Due to the inaccuracy of contour vertexes for describing object instances, mask decay, and contour decay issues arise, limiting the performances of contour-based instance segmentation methods. In order to address these issues, in this article, we propose to design a contour and enclosed region refining network module, named CORE2, to integrate basic contour-based instance segmentation methods to obtain high-quality instance segmentation results. Specifically, we adopt a graph convolutional network to utilize correlation among initially predicted contour vertexes for refinement to address the contour decay issue. And, we predict and assemble a set of boundary-aware heatmaps to eliminate external regions enclosed within predicted object instance contours to relieve the mask decay problem. Furthermore, we propose several improvements that can be made to a basic contour-based instance segmentation method, i.e., polar generalized intersection over union loss, internal center, and hard sample polar centerness. Finally, extensive experiments are conducted on the COCO data set to evaluate the effectiveness of the proposed method. Experimental results show that our method can achieve 39.8 mean average precision on the COCO data set, which outperforms state-of-the-art contour-based instance segmentation methods.