Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation
This work addresses the problem of reducing expensive mask annotations for instance segmentation, with incremental contributions by combining shape and appearance modeling.
The paper tackles partially supervised instance segmentation by learning class-agnostic commonalities in shape and appearance from limited mask-annotated categories, achieving significant performance improvements over state-of-the-art methods on the COCO dataset.
Partially supervised instance segmentation aims to perform learning on limited mask-annotated categories of data thus eliminating expensive and exhaustive mask annotation. The learned models are expected to be generalizable to novel categories. Existing methods either learn a transfer function from detection to segmentation, or cluster shape priors for segmenting novel categories. We propose to learn the underlying class-agnostic commonalities that can be generalized from mask-annotated categories to novel categories. Specifically, we parse two types of commonalities: 1) shape commonalities which are learned by performing supervised learning on instance boundary prediction; and 2) appearance commonalities which are captured by modeling pairwise affinities among pixels of feature maps to optimize the separability between instance and the background. Incorporating both the shape and appearance commonalities, our model significantly outperforms the state-of-the-art methods on both partially supervised setting and few-shot setting for instance segmentation on COCO dataset.