Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

by   Lei Ke, et al.

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries. Unlike previous two-stage instance segmentation methods, we model image formation as composition of two overlapping layers, and propose Bilayer Convolutional Network (BCNet), where the top GCN layer detects the occluding objects (occluder) and the bottom GCN layer infers partially occluded instance (occludee). The explicit modeling of occlusion relationship with bilayer structure naturally decouples the boundaries of both the occluding and occluded instances, and considers the interaction between them during mask regression. We validate the efficacy of bilayer decoupling on both one-stage and two-stage object detectors with different backbones and network layer choices. Despite its simplicity, extensive experiments on COCO and KINS show that our occlusion-aware BCNet achieves large and consistent performance gain especially for heavy occlusion cases. Code is available at



page 2

page 3

page 4

page 7

page 8


Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling

Instance-aware segmentation of unseen objects is essential for a robotic...

BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation

Panoptic segmentation aims to perform instance segmentation for foregrou...

Human Instance Matting via Mutual Guidance and Multi-Instance Refinement

This paper introduces a new matting task called human instance matting (...

Layered Embeddings for Amodal Instance Segmentation

The proposed method extends upon the representational output of semantic...

Occluded Video Instance Segmentation

Can our video understanding systems perceive objects when a heavy occlus...

OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding

To effectively apply robots in working environments and assist humans, i...

Occlusion-shared and Feature-separated Network for Occlusion Relationship Reasoning

Occlusion relationship reasoning demands closed contour to express the o...

Code Repositories


Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.