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. © 2019 IEEE.

Keywords

Computer scienceContext (archaeology)Block (permutation group theory)ComputationPosition (finance)Property (philosophy)Range (aeronautics)Theoretical computer scienceConstruct (python library)Data miningDistributed computingAlgorithmMathematicsComputer network

Affiliated Institutions

Related Publications

Squeeze-and-Excitation Networks

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial a...

2019 IEEE Transactions on Pattern Analysis... 12023 citations

Squeeze-and-Excitation Networks

Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local ...

2018 25361 citations

Publication Info

Year
2019
Type
preprint
Citations
1952
Access
Closed

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1952
OpenAlex
170
Influential
1673
CrossRef

Cite This

Yue Cao, Jiarui Xu, Stephen Lin et al. (2019). GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) . https://doi.org/10.1109/iccvw.2019.00246

Identifiers

DOI
10.1109/iccvw.2019.00246
arXiv
1904.11492

Data Quality

Data completeness: 84%