The task of instance segmentation is widely acknowledged as being one of the most formidable challenges in the field of computer vision. Current methods have low utilization of boundary information, especially in dense scenes with occlusion and complex shapes of object instances, the boundary information may become ineffective. This results in coarse object boundary masks that fail to cover the entire object. To address this challenge, we are introducing a novel method called boundary-guided global feature fusion (BGF) which is based on the Mask R-CNN network. We designed a boundary branch that includes a Boundary Feature Extractor (BFE) module to extract object boundary features at different stages. Additionally, we constructed a binary image dataset containing instance boundaries for training the boundary branch. We also trained the boundary branch separately using a dedicated dataset before training the entire network. We then input the Mask R-CNN features and boundary features into a feature fusion module where the boundary features provide shape information needed for detection and segmentation. Finally, we use a global attention module (GAM) to further fuse features. Through extensive experiments, we demonstrate that our approach outperforms state-of-the-art instance segmentation algorithms, producing finer and more complete instance masks while also improving model capability.

实例分割任务被广泛认为是计算机视觉领域最艰巨的挑战之一。目前的方法对边界信息的利用率较低，特别是在具有遮挡和对象实例形状复杂的密集场景中，边界信息可能变得无效。这会导致对象边界掩模粗糙，无法覆盖整个对象。为了应对这一挑战，我们引入了一种称为边界引导全局特征融合 (BGF) 的新方法，该方法基于 Mask R-CNN 网络。我们设计了一个边界分支，其中包括边界特征提取器（BFE）模块，用于提取不同阶段的对象边界特征。此外，我们构建了一个包含实例边界的二进制图像数据集，用于训练边界分支。在训练整个网络之前，我们还使用专用数据集单独训练边界分支。然后，我们将 Mask R-CNN 特征和边界特征输入到特征融合模块中，其中边界特征提供检测和分割所需的形状信息。最后，我们使用全局注意力模块（GAM）来进一步融合特征。通过大量的实验，我们证明我们的方法优于最先进的实例分割算法，产生更精细、更完整的实例掩模，同时还提高了模型能力。