Description
A Global Context Network, or GCNet, utilises global context blocks to model long-range dependencies in images. It is based on the Non-Local Network, but it modifies the architecture so less computation is required. Global context blocks are applied to multiple layers in a backbone network to construct the GCNet.
Papers Using This Method
Golden Cudgel Network for Real-Time Semantic Segmentation2025-03-05GCNet: Probing Self-Similarity Learning for Generalized Counting Network2023-02-10GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation2022-03-04GCNET: graph-based prediction of stock price movement using graph convolutional network2022-02-19Leveraging Inlier Correspondences Proportion for Point Cloud Registration2022-01-28Weakly-Supervised Metric Learning With Cross-Module Communications for the Classification of Anterior Chamber Angle Images2022-01-01Bilateral Grid Learning for Stereo Matching Networks2021-06-19Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking2021-03-23Global Context Networks2020-12-24Do End-to-end Stereo Algorithms Under-utilize Information?2020-10-14GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond2019-04-25