Methods > Computer Vision > Image Model Blocks

Global Context Block

Introduced by Cao et al. in GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

A Global Context Block is an image model block for global context modeling. The aim is to have both the benefits of the simplified non-local block with effective modeling of long-range dependencies, and the squeeze-excitation block with lightweight computation.

In the Global Context framework, we have (a) global attention pooling, which adopts a 1x1 convolution $W_{k}$ and softmax function to obtain the attention weights, and then performs the attention pooling to obtain the global context features, (b) feature transform via a 1x1 convolution $W_{v}$; (c) feature aggregation, which employs addition to aggregate the global context features to the features of each position. Taken as a whole, the GC block is proposed as a lightweight way to achieve global context modeling.

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

Latest Papers

PAPER DATE
Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking
Xuewu LinYu-ang GuoJianqiang Wang
2021-03-23
Bilateral Grid Learning for Stereo Matching Networks
Bin XuYuhua XuXiaoli YangWei JiaYulan Guo
2021-01-01
Global Context Networks
| Yue CaoJiarui XuStephen LinFangyun WeiHan Hu
2020-12-24
Do End-to-end Stereo Algorithms Under-utilize Information?
| Changjiang CaiPhilippos Mordohai
2020-10-14
AWNet: Attentive Wavelet Network for Image ISP
| Linhui DaiXiaohong LiuChengqi LiJun Chen
2020-08-20
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
| Yue CaoJiarui XuStephen LinFangyun WeiHan Hu
2019-04-25

Tasks

Categories