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

Code

• github.com/xvjiarui/GCNet
  OfficialIn paperpytorch★ 1,221
• github.com/open-mmlab/mmdetection
  pytorch★ 32,525
• github.com/open-mmlab/mmsegmentation
  pytorch★ 9,690
• github.com/PaddlePaddle/PaddleSeg
  paddle★ 9,319
• github.com/open-mmlab/mmpose
  pytorch★ 7,439
• github.com/zhusiling/GCNet
  pytorch★ 0
• github.com/xggIoU/GCNet_global_context_module_tensorflow
  tf★ 0
• github.com/czero69/acomoeye-NN
  tf★ 0
• github.com/Oichii/DeepPulse-pytorch
  pytorch★ 0

Abstract

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by non-local network are almost the same for different query positions within an image. In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further observe that this simplified design shares similar structure with Squeeze-Excitation Network (SENet). Hence we unify them into a three-step general framework for global context modeling. Within the general framework, we design a better instantiation, called the global context (GC) block, which is lightweight and can effectively model the global context. The lightweight property allows us to apply it for multiple layers in a backbone network to construct a global context network (GCNet), which generally outperforms both simplified NLNet and SENet on major benchmarks for various recognition tasks. The code and configurations are released at https://github.com/xvjiarui/GCNet.

Tasks

Benchmark Results

Reproductions