Amodal Instance Segmentation via Prior-Guided Expansion

Amodal instance segmentation aims to infer the amodal mask, including both the visible part and occluded part of each object instance. Predicting the occluded parts is challenging. Existing methods often produce incomplete amodal boxes and amodal masks, probably due to lacking visual evidences to expand the boxes and masks. To this end, we propose a prior-guided expansion framework, which builds on a two-stage segmentation model (i.e., Mask R-CNN) and performs box-level (resp., pixel-level) expansion for amodal box (resp., mask) prediction, by retrieving regression (resp., flow) transformations from a memory bank of expansion prior. We conduct extensive experiments on KINS, D2SA, and COCOA cls datasets, which show the effectiveness of our method.

Authors

• Junjie Chen The University of Tokyo
• Li Niu Shanghai Jiao Tong University
• Jianfu Zhang Shanghai Jiaotong University
• Jianlou Si SenseTime
• Chen Qian SenseTime Research and Tetras.AI
• Liqing Zhang

Keywords

• CV: Segmentation