Instance Segmentation Models

A Global Context Network, or GCNet, utilises global context blocks to model long-range dependencies in images. It is based on the Non-Local Network, but it modifies the architecture so less computation is required. Global context blocks are applied to multiple layers in a backbone network to construct the GCNet.

Source: GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond


Paper Code Results Date Stars


Task Papers Share
Object Detection 3 18.75%
Stereo Matching 2 12.50%
Instance Segmentation 2 12.50%
Point Cloud Registration 1 6.25%
Metric Learning 1 6.25%
Robot Navigation 1 6.25%
Association 1 6.25%
Management 1 6.25%
Multi-Object Tracking 1 6.25%