Methods › General › Skip Connection Blocks › Global Context Block
Global Context Block
Introduced by Yue Cao et al. in GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 Wₖ 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 Wᵥ; (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.
Papers archive 2025-07-28
12 shown of 12, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Golden Cudgel Network for Real-Time Semantic Segmentation 5 Mar 2025 · 1 repository · arXiv:2503.03325
-
GCNet: Probing Self-Similarity Learning for Generalized Counting Network 10 Feb 2023 · 0 repositories · arXiv:2302.05132
-
GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation 4 Mar 2022 · 1 repository · arXiv:2203.02177
-
GCNET: graph-based prediction of stock price movement using graph convolutional network 19 Feb 2022 · 1 repository · arXiv:2203.11091
-
Leveraging Inlier Correspondences Proportion for Point Cloud Registration 28 Jan 2022 · 1 repository · arXiv:2201.12094
-
Weakly-Supervised Metric Learning With Cross-Module Communications for the Classification of Anterior Chamber Angle Images 1 Jan 2022 · 1 repository
-
Bilateral Grid Learning for Stereo Matching Networks 19 Jun 2021 · 1 repository · arXiv:2101.01601Syntology ran 15 of 18 samples · 3 unverified · 18 pointer-only (licence)
-
Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking 23 Mar 2021 · 0 repositories · arXiv:2103.12511
-
Global Context Networks 24 Dec 2020 · 3 repositories · arXiv:2012.13375
-
Do End-to-end Stereo Algorithms Under-utilize Information? 14 Oct 2020 · 1 repository · arXiv:2010.07350
-
AWNet: Attentive Wavelet Network for Image ISP 20 Aug 2020 · 1 repository · arXiv:2008.09228
-
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond 25 Apr 2019 · 9 repositories · arXiv:1904.11492
Tasks archive 2025-07-28
18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections