BSOLO: Boundary-Aware One-Stage Instance Segmentation SOLO

Current one-stage instance segmentation methods ignore the boundary information of masks, resulting in coarse masks that are far from the ground truth. In this paper, we propose a boundary-aware method to refine boundary information, called BSOLO. The core idea of BSOLO is to design a Hungarian-Algorithm-based boundary loss to calculate matching costs between boundaries. This loss effectively measures the difference between boundaries and suits for boundary regression, contributing to generating refined instance masks with high-quality boundaries. Besides, we propose a Feature Fusion Network (FFN) to capture long-range dependency. Through constructing the relationship between pixels, such a module is beneficial for predicting masks with large or uncontinuous region. Furthermore, we introduce a Prototype Attention Module (PAM) for mask assembling through channel attention, which enhances informative features and spotlights important prototypes. To evaluate the performance of BSOLO, we conduct extensive experiments. Experimental results show that BSOLO achieves 39.3 AP on MS COCO test-dev2017, outperforming SOLO and other methods by a large margin. We hope that BSOLO broadens the perspective for designing more valid boundary constraints.