The key to a successful cascade architecture for precise instance
segmentation is to fully leverage the relationship between bounding box
detection and mask segmentation across multiple stages. Although modern
instance segmentation cascades achieve leading performance, they mainly make
use of a unidirectional relationship, i.e., mask segmentation can benefit from
iteratively refined bounding box detection. In this paper, we investigate an
alternative direction, i.e., how to take the advantage of precise mask
segmentation for bounding box detection in a cascade architecture. We propose a
Deeply Shape-guided Cascade (DSC) for instance segmentation, which iteratively
imposes the shape guidances extracted from mask prediction at the previous
stage on bounding box detection at current stage. It forms a bi-directional
relationship between the two tasks by introducing three key components: (1)
Initial shape guidance: A mask-supervised Region Proposal Network (mPRN) with
the ability to generate class-agnostic masks; (2) Explicit shape guidance: A
mask-guided region-of-interest (RoI) feature extractor, which employs mask
segmentation at previous stage to focus feature extraction at current stage
within a region aligned well with the shape of the instance-of-interest rather
than a rectangular RoI; (3) Implicit shape guidance: A feature fusion operation
which feeds intermediate mask features at previous stage to the bounding box
head at current stage. Experimental results show that DSC outperforms the
state-of-the-art instance segmentation cascade, Hybrid Task Cascade (HTC), by a
large margin and achieves 51.8 box AP and 45.5 mask AP on COCO test-dev. The
code is released at: this https URL

本文提出了一种深度形状引导级联算法 (DSC)，通过引入三种关键组件，即初始形状指导、显式形状指导和隐式形状指导，使掩模分割和边界框检测形成双向关系，进而提高了实例分割的性能。实验结果表明，DSC 较当前最先进的实例分割算法 Hybrid Task Cascade (HTC) 提升明显，在 COCO 测试中获得了 51.8 的 box AP 和 45.5 的 mask AP。