{"url":"/method/global-context-block","slug":"global-context-block","name":"Global Context Block","full_name":"Global Context Block","full_name_withheld":false,"description_markdown":"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](https://paperswithcode.com/method/non-local-block) with effective modeling of long-range dependencies, and the [squeeze-excitation block](https://paperswithcode.com/method/squeeze-and-excitation-block) with lightweight computation. \r\n\r\nIn the Global Context framework, we have (a) global attention pooling, which adopts a [1x1 convolution](https://paperswithcode.com/method/1x1-convolution) $W_{k}$ and [softmax](https://paperswithcode.com/method/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](https://paperswithcode.com/method/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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","paper":"/paper/gcnet-non-local-networks-meet-squeeze","first_author":"Yue Cao","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/gcnet-non-local-networks-meet-squeeze"},"source":{"url":"http://arxiv.org/abs/1904.11492v1","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/xvjiarui/GCNet/blob/a9fcc88c4bd3a0b89de3678b4629c9dfd190575f/mmdet/ops/gcb/context_block.py#L13","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Skip Connection Blocks","url":"/methods/category/skip-connection-blocks","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Attention Modules","url":"/methods/category/attention-modules","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Model Blocks","url":"/methods/category/image-model-blocks","pwc_aliases":[]}],"n_papers_tagged":12,"archive_num_papers":12,"papers_newest_first":[{"paper":"/paper/golden-cudgel-network-for-real-time-semantic","title":"Golden Cudgel Network for Real-Time Semantic Segmentation","date":"2025-03-05","arxiv_id":"2503.03325","n_code_links":1,"syntology":null},{"paper":null,"title":"GCNet: Probing Self-Similarity Learning for Generalized Counting Network","date":"2023-02-10","arxiv_id":"2302.05132","n_code_links":0,"syntology":null},{"paper":"/paper/gcnet-graph-completion-network-for-incomplete","title":"GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation","date":"2022-03-04","arxiv_id":"2203.02177","n_code_links":1,"syntology":null},{"paper":"/paper/gcnet-graph-based-prediction-of-stock-price","title":"GCNET: graph-based prediction of stock price movement using graph convolutional network","date":"2022-02-19","arxiv_id":"2203.11091","n_code_links":1,"syntology":null},{"paper":"/paper/neighborhood-aware-geometric-encoding-network","title":"Leveraging Inlier Correspondences Proportion for Point Cloud Registration","date":"2022-01-28","arxiv_id":"2201.12094","n_code_links":1,"syntology":null},{"paper":"/paper/weakly-supervised-metric-learning-with-cross","title":"Weakly-Supervised Metric Learning With Cross-Module Communications for the Classification of Anterior Chamber Angle Images","date":"2022-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/bilateral-grid-learning-for-stereo-matching","title":"Bilateral Grid Learning for Stereo Matching Networks","date":"2021-06-19","arxiv_id":"2101.01601","n_code_links":1,"syntology":{"ran":15,"of":18,"unverified":3,"pointer_only":18}},{"paper":null,"title":"Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking","date":"2021-03-23","arxiv_id":"2103.12511","n_code_links":0,"syntology":null},{"paper":"/paper/global-context-networks","title":"Global Context Networks","date":"2020-12-24","arxiv_id":"2012.13375","n_code_links":3,"syntology":null},{"paper":"/paper/do-end-to-end-stereo-algorithms-under-utilize","title":"Do End-to-end Stereo Algorithms Under-utilize Information?","date":"2020-10-14","arxiv_id":"2010.07350","n_code_links":1,"syntology":null},{"paper":"/paper/awnet-attentive-wavelet-network-for-image-isp","title":"AWNet: Attentive Wavelet Network for Image ISP","date":"2020-08-20","arxiv_id":"2008.09228","n_code_links":1,"syntology":null},{"paper":"/paper/gcnet-non-local-networks-meet-squeeze","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","date":"2019-04-25","arxiv_id":"1904.11492","n_code_links":9,"syntology":null}],"papers_shown":12,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":2},{"task":"/task/stereo-matching-1","name":"Stereo Matching","papers":2},{"task":"/task/disparity-estimation","name":"Disparity Estimation","papers":1},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":1},{"task":"/task/management","name":"Management","papers":1},{"task":"/task/metric-learning","name":"Metric Learning","papers":1},{"task":"/task/multi-object-tracking","name":"Multi-Object Tracking","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/object-recognition","name":"Object Recognition","papers":1},{"task":"/task/object-tracking","name":"Object Tracking","papers":1},{"task":"/task/point-cloud-registration","name":"Point Cloud Registration","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/real-time-semantic-segmentation","name":"Real-Time Semantic Segmentation","papers":1},{"task":"/task/robot-navigation","name":"Robot Navigation","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":18,"n_tasks":18,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":3},{"year":"2021","papers":2},{"year":"2022","papers":4},{"year":"2023","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/global-context-block"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}