Skip to content

Latest commit

 

History

History
 
 

gcnet

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

GCNet

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

Introduction

Official Repo

Code Snippet

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 this https URL.

Results and models

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) Device mIoU mIoU(ms+flip) config download
GCNet R-50-D8 512x1024 40000 5.8 3.93 V100 77.69 78.56 config model | log
GCNet R-101-D8 512x1024 40000 9.2 2.61 V100 78.28 79.34 config model | log
GCNet R-50-D8 769x769 40000 6.5 1.67 V100 78.12 80.09 config model | log
GCNet R-101-D8 769x769 40000 10.5 1.13 V100 78.95 80.71 config model | log
GCNet R-50-D8 512x1024 80000 - - V100 78.48 80.01 config model | log
GCNet R-101-D8 512x1024 80000 - - V100 79.03 79.84 config model | log
GCNet R-50-D8 769x769 80000 - - V100 78.68 80.66 config model | log
GCNet R-101-D8 769x769 80000 - - V100 79.18 80.71 config model | log

ADE20K

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) Device mIoU mIoU(ms+flip) config download
GCNet R-50-D8 512x512 80000 8.5 23.38 V100 41.47 42.85 config model | log
GCNet R-101-D8 512x512 80000 12 15.20 V100 42.82 44.54 config model | log
GCNet R-50-D8 512x512 160000 - - V100 42.37 43.52 config model | log
GCNet R-101-D8 512x512 160000 - - V100 43.69 45.21 config model | log

Pascal VOC 2012 + Aug

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) Device mIoU mIoU(ms+flip) config download
GCNet R-50-D8 512x512 20000 5.8 23.35 V100 76.42 77.51 config model | log
GCNet R-101-D8 512x512 20000 9.2 14.80 V100 77.41 78.56 config model | log
GCNet R-50-D8 512x512 40000 - - V100 76.24 77.63 config model | log
GCNet R-101-D8 512x512 40000 - - V100 77.84 78.59 config model | log

Citation

@inproceedings{cao2019gcnet,
  title={Gcnet: Non-local networks meet squeeze-excitation networks and beyond},
  author={Cao, Yue and Xu, Jiarui and Lin, Stephen and Wei, Fangyun and Hu, Han},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision Workshops},
  pages={0--0},
  year={2019}
}