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 BeyondPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 3 | 13.64% |
Decoder | 2 | 9.09% |
Stereo Matching | 2 | 9.09% |
Instance Segmentation | 2 | 9.09% |
Real-Time Semantic Segmentation | 1 | 4.55% |
Semantic Segmentation | 1 | 4.55% |
Graph Neural Network | 1 | 4.55% |
Prediction | 1 | 4.55% |
Point Cloud Registration | 1 | 4.55% |