Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation

ECCV 2020  ·  Qi Fan, Lei Ke, Wenjie Pei, Chi-Keung Tang, Yu-Wing Tai ·

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. read more

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Instance Segmentation COCO test-dev CPMask mask AP 39.2 # 41
AP50 60.8 # 21
AP75 42.2 # 18
APS 22.2 # 12
APM 41.8 # 19
APL 50.1 # 25

Methods


No methods listed for this paper. Add relevant methods here